Platform Architect - Search & Retrieval Systems Job at AlphaSense (Bengaluru)

Principal AI Engineer

We are looking for a Principal AI Engineer to lead the design and deployment of ...

Location

United States

Salary:

200000.00 - 300000.00 USD / Year

Apollo.io

Expiration Date

Until further notice

Requirements

10+ years of software engineering experience
at least 3 years in applied LLM or agentic AI systems (2023–present)
proven success in deploying LLM-powered products used by real users at scale
deep backend & systems engineering expertise with Python, distributed systems, and scalable APIs
familiarity with LangChain, LlamaIndex, or similar orchestration frameworks
experience with RAG pipelines, vector DBs, embedding models, and semantic search tuning
experience managing performance across cloud providers (e.g., AWS Bedrock, OpenAI, Anthropic, etc.)
demonstrated experience building multi-step agents, planning workflows, chaining reasoning steps, and integrating APIs with agent memory/state
comfort with advanced prompting strategies, few-shot and chain-of-thought reasoning, and embedding retrieval setups
strong understanding of AI system evaluation, human ratings, A/B experimentation, and feedback loop pipelines

Job Responsibility

Architect and lead the development of multi-agent systems capable of long-horizon planning, reasoning, and API orchestration
build reusable agentic components that integrate deeply into sales and marketing processes
own and evolve our in-house platform for scalable, low-latency, and cost-efficient LLM and agent deployments
lead design of interfaces powered by natural language understanding and retrieval-augmented generation (RAG)
build embedding-based, intent-aware search and personalization systems tuned to business user needs
drive innovation in personalized outreach generation using context-aware generation pipelines
tune inference pipelines, caching layers, and model selection logic for high-scale, cost-aware performance
define and drive robust offline and online testing methodologies (A/B, sandboxing, human evals) across agents and LLM flows
architect human-in-the-loop systems and telemetry to improve accuracy, UX, and explainability over time

What we offer

equity
company bonus or sales commissions/bonuses
401(k) plan
at least 10 paid holidays per year
flex PTO
parental leave
employee assistance program
wellbeing benefits
global travel coverage
life/AD&D/STD/LTD insurance

Fulltime

New

Staff Application Engineer, Workplace Technology

The role is part of the IT Function within the broader Mozilla Infrastructure te...

Location

United States; Canada

Salary:

Not provided

Mozilla

Expiration Date

Until further notice

Requirements

7–10 years of software engineering or automation experience, including experience building scalable systems, integrations and agentic workflows in enterprise environments
Strong software design and development skills in Java, Go, Python, JavaScript/TypeScript (or Apps Script), or equivalent languages
experience with building production-ready services and agentic systems
Deep experience integrating SaaS platforms (collaboration tools, identity systems) using APIs, SDKs, event-driven architectures, and building automation/agent orchestration layers
Familiarity with IAM/SSO (Okta, SAML/OIDC/SCIM), lifecycle automation and securing access across humans and agents
experience embedding governance into automation flows
Proven ability to design for reliability, security, scalability and cost-efficiency
strong experience with observability, metrics and monitoring frameworks for automated/agentic services
Demonstrated ability to lead the technical direction of automation and agentic workflows: build shared libraries, connectors, guide architecture, mentor others, influence cross-team engineering culture
Experience or willingness to work with GenAI/LLM modalities (agent design, prompt management, retrieval + RAG, integrations) and build operational patterns around them (e.g., agent orchestration, trust, guardrails)

Job Responsibility

Architect, develop, and scale automation frameworks, integrations and agentic workflows across Mozilla’s workplace technology ecosystem — including collaboration tools, identity systems (SSO/IAM), and GenAI platforms (OpenAI, Claude, Gemini)
Lead end-to-end engineering of lifecycle workflows (onboarding, off-boarding, access provisioning) using APIs, event-driven architectures and intelligent agentic flows that reduce manual touchpoints and accelerate user access
Build and maintain reusable libraries, connectors, SDKs and agent orchestration layers (e.g., virtual assistants, workflow agents, RAG + retrieval pipelines) that enable faster, safer AI-enabled productivity at scale
Implement observability for agentic workflows and automations: define metrics (SLIs/SLOs), build dashboards, logging, alerts and proactively tune for reliability, security, cost-efficiency and adoption
Partner with Security, Legal, and Privacy to embed DLP, data classification, and least-privilege access into automation and AI flows — ensure agentic capabilities respect governance, auditing, and compliance
Lead evaluation, technical design, and production deployment of new tools and AI productivity platforms: architect integrations, define guardrails, pilot agentic features, measure adoption and user impact
Mentor junior engineers and facilitate collaboration across teams: review design/code, establish best practices for building agentic systems, guide documentation and champion a shared automation culture
Collaborate cross-functionally with IT, Security, Finance, People Ops and Workplace/Facilities to deliver secure, efficient, and scalable internal tools and workflows that empower users and optimize operations
Drive innovation through prototyping next-gen agentic services (for example: intelligent enterprise search assistants, document-to-action bots, contextual collaboration agents) to increase productivity and reduce friction

What we offer

Generous performance-based bonus plans to all eligible employees
Rich medical, dental, and vision coverage
Generous retirement contributions with 100% immediate vesting
Quarterly all-company wellness days where everyone takes a pause together
Country specific holidays plus a day off for your birthday
One-time home office stipend
Annual professional development budget
Quarterly well-being stipend
Considerable paid parental leave
Employee referral bonus program

Fulltime

Staff Application Engineer, Workplace Technology

The role is part of the IT Function within the broader Mozilla Infrastructure te...

Location

United States; Canada

Salary:

Not provided

Mozilla

Expiration Date

Until further notice

Requirements

7–10 years of software engineering or automation experience, including experience building scalable systems, integrations and agentic workflows in enterprise environments
Strong software design and development skills in Java, Go, Python, JavaScript/TypeScript (or Apps Script), or equivalent languages
experience with building production-ready services and agentic systems
Deep experience integrating SaaS platforms (collaboration tools, identity systems) using APIs, SDKs, event-driven architectures, and building automation/agent orchestration layers
Familiarity with IAM/SSO (Okta, SAML/OIDC/SCIM), lifecycle automation and securing access across humans and agents
experience embedding governance into automation flows
Proven ability to design for reliability, security, scalability and cost-efficiency
strong experience with observability, metrics and monitoring frameworks for automated/agentic services
Demonstrated ability to lead the technical direction of automation and agentic workflows: build shared libraries, connectors, guide architecture, mentor others, influence cross-team engineering culture
Experience or willingness to work with GenAI/LLM modalities (agent design, prompt management, retrieval + RAG, integrations) and build operational patterns around them (e.g., agent orchestration, trust, guardrails)

Job Responsibility

Architect, develop, and scale automation frameworks, integrations and agentic workflows across Mozilla’s workplace technology ecosystem — including collaboration tools, identity systems (SSO/IAM), and GenAI platforms (OpenAI, Claude, Gemini)
Lead end-to-end engineering of lifecycle workflows (onboarding, off-boarding, access provisioning) using APIs, event-driven architectures and intelligent agentic flows that reduce manual touchpoints and accelerate user access
Build and maintain reusable libraries, connectors, SDKs and agent orchestration layers (e.g., virtual assistants, workflow agents, RAG + retrieval pipelines) that enable faster, safer AI-enabled productivity at scale
Implement observability for agentic workflows and automations: define metrics (SLIs/SLOs), build dashboards, logging, alerts and proactively tune for reliability, security, cost-efficiency and adoption
Partner with Security, Legal, and Privacy to embed DLP, data classification, and least-privilege access into automation and AI flows — ensure agentic capabilities respect governance, auditing, and compliance
Lead evaluation, technical design, and production deployment of new tools and AI productivity platforms: architect integrations, define guardrails, pilot agentic features, measure adoption and user impact
Mentor junior engineers and facilitate collaboration across teams: review design/code, establish best practices for building agentic systems, guide documentation and champion a shared automation culture
Collaborate cross-functionally with IT, Security, Finance, People Ops and Workplace/Facilities to deliver secure, efficient, and scalable internal tools and workflows that empower users and optimize operations
Drive innovation through prototyping next-gen agentic services (for example: intelligent enterprise search assistants, document-to-action bots, contextual collaboration agents) to increase productivity and reduce friction

What we offer

Generous performance-based bonus plans to all eligible employees
Rich medical, dental, and vision coverage
Generous retirement contributions with 100% immediate vesting (regardless of whether you contribute)
Quarterly all-company wellness days where everyone takes a pause together
Country specific holidays plus a day off for your birthday
One-time home office stipend
Annual professional development budget
Quarterly well-being stipend
Considerable paid parental leave
Employee referral bonus program

Fulltime

New

LLM Engineer

You will join our global Machine Learning and Data Science unit — a core team of...

Location

Poland , Warsaw

Salary:

Not provided

Gipo

Expiration Date

Until further notice

Requirements

At least one year of professional experience in LLM development or integration in a fast-paced, product-driven tech environment
Demonstrated expertise in production-grade LLM deployments, including prompt management systems, vector databases, semantic search implementation, and API integration with foundation models
Good understanding of transformer architectures and proficiency in LLM frameworks such as LangChain, LlamaIndex, or similar tools
Proficiency in Python
Experience in collaborative project development
Appreciation for good engineering practices and maintainable code
Proven experience in evaluating LLMs through systematic testing, benchmark design, and the development of custom metrics (e.g. accuracy, consistency, factuality, and bias), with a focus on aligning results to product and user needs
Proven ability to integrate, deploy, and optimize large language models in production-grade industry environments, ensuring scalability and robust performance
Strong knowledge in prompt engineering, agent-based workflows, and the generation and manipulation of embeddings
Experience with RAG (Retrieval-Augmented Generation) techniques, vector similarity search, and information retrieval methods to enhance LLM capabilities

Job Responsibility

Work closely with cross-functional teams, including scientists, engineers, and product stakeholders, to deliver LLM-driven initiatives that directly contribute to business objectives
Design, deploy and iterate over LLM services for text-based applications (and beyond), while proactively identifying and eliminating performance bottlenecks
Build small to medium-sized Python projects and collaborate with engineers on production code and deployments at scale
Assess platform engineering and LLMOps bottlenecks
research and design scalable prompt management strategies, and recommend solutions that balance performance, cost, and reliability
Research, architect, and deploy LLM-powered information retrieval solutions (e.g., RAG) to deliver accurate results in complex, multilingual product environments
Partner with the AI Platform team to refine LLMOps best practices, evolve frameworks, and establish efficient, scalable workflows

What we offer

Share options plan after 6 months of working with us
Remote or hybrid work model with or hub in Warsaw
Flexible working hours (fully flexible, as in most cases you only have to be on a couple of meetings weekly)
20/26 days of paid time off (depending on your contract)
Additional paid day off on your birthday or work anniversary (you choose what you want to celebrate)
Private healthcare plan with Signal Iduna for you and subsidized for your family
Multisport card co-financing for you to have access to sports facilities across Poland
Access to iFeel, a technological platform for mental wellness offering online psychological support and counseling
Free English classes

Fulltime

New

LLM Engineer

You will join our global Machine Learning and Data Science unit — a core team of...

Location

Spain , Barcelona

Salary:

Not provided

Gipo

Expiration Date

Until further notice

Requirements

At least one year of professional experience in LLM development or integration in a fast-paced, product-driven tech environment
Demonstrated expertise in production-grade LLM deployments, including prompt management systems, vector databases, semantic search implementation, and API integration with foundation models
Good understanding of transformer architectures and proficiency in LLM frameworks such as LangChain, LlamaIndex, or similar tools
Proficiency in Python
Experience in collaborative project development
Appreciation for good engineering practices and maintainable code
Proven experience in evaluating LLMs through systematic testing, benchmark design, and the development of custom metrics (e.g. accuracy, consistency, factuality, and bias), with a focus on aligning results to product and user needs
Proven ability to integrate, deploy, and optimize large language models in production-grade industry environments, ensuring scalability and robust performance
Strong knowledge in prompt engineering, agent-based workflows, and the generation and manipulation of embeddings
Experience with RAG (Retrieval-Augmented Generation) techniques, vector similarity search, and information retrieval methods to enhance LLM capabilities

Job Responsibility

Work closely with cross-functional teams, including scientists, engineers, and product stakeholders, to deliver LLM-driven initiatives that directly contribute to business objectives
Design, deploy and iterate over LLM services for text-based applications (and beyond), while proactively identifying and eliminating performance bottlenecks
Build small to medium-sized Python projects and collaborate with engineers on production code and deployments at scale
Assess platform engineering and LLMOps bottlenecks
research and design scalable prompt management strategies, and recommend solutions that balance performance, cost, and reliability
Research, architect, and deploy LLM-powered information retrieval solutions (e.g., RAG) to deliver accurate results in complex, multilingual product environments
Partner with the AI Platform team to refine LLMOps best practices, evolve frameworks, and establish efficient, scalable workflows

What we offer

Flexible remuneration and benefits system via Flexoh, which includes: restaurant card, transportation card, kindergarten, and training tax savings
Share options plan after 6 months of working with us
Remote or hybrid work model with our hub in Barcelona
Flexible working hours (fully flexible, as in most cases you only have to be on a couple of meetings weekly)
Summer intensive schedule during July and August (work 7 hours, finish earlier)
23 paid holidays, with exchangeable local bank holidays
Additional paid holiday on your birthday or work anniversary (you choose what you want to celebrate)
Private healthcare plan with Adeslas for you and subsidized for your family (medical and dental)
Access to hundreds of gyms for a symbolic fee in partnership for you and your family with Wellhub
Access to iFeel, a technological platform for mental wellness offering online psychological support and counseling

Fulltime

Data Scientist

This role is ideal for an AI professional who thrives in designing LLM-driven pi...

Location

Salary:

Not provided

HurixDigital

Expiration Date

Until further notice

Requirements

2–4 years of experience in Data Science, AI/ML, and Deep Learning, preferably in enterprise settings
Strong experience with Python, TensorFlow/Keras, Scikit-learn, and NLP frameworks such as SpaCy, HuggingFace, and NLTK
Proven expertise in Generative AI systems, including RAG architecture, vector-based search, and prompt engineering
Solid hands-on experience with Azure Cloud Platform, including services like Azure OpenAI, Cosmos DB, Key Vault, Blob Storage, Function Apps, etc.
Proficiency with FastAPI, Flask, and RESTful API design
Experience deploying models and services using Docker, Kubernetes, and Azure DevOps
Familiarity with Power Platform (Power BI, Power Apps, Power Automate) and SharePoint integration

Job Responsibility

Architect and implement Retrieval-Augmented Generation (RAG) pipelines using tools like LangChain, LlamaIndex, and Azure AI Search
Design and coordinate agent-based LLM systems using frameworks like AutoGen, TaskWeaver, and CrewAI for complex document analysis and process automation
Integrate Azure Cognitive Services (OCR, layout analysis, document intelligence) for structured data extraction and real-time insight generation
Develop secure and scalable FastAPI backends, containerized via Docker and orchestrated on Azure Kubernetes Service (AKS)
Collaborate with business experts to fine-tune prompts, build chatbots with contextual memory, and deploy solutions that meet compliance and audit standards
Build low-code applications using Power Apps and Power Automate to streamline enterprise workflows like workforce planning and financial tracking
Monitor model performance using Azure Application Insights, iterate on user feedback, and maintain operational excellence with CI/CD pipelines
Contribute to AI research and publications and stay updated with the latest trends in ethical AI and edge deployment strategies

Fulltime

New

Senior Data Engineer - AI Focused

At Doctolib, we're on a mission to transform healthcare through the power of AI....

Location

France , Paris

Salary:

Not provided

Doctolib

Expiration Date

Until further notice

Requirements

Master’s or Ph.D. degree in Computer Science, Data Engineering, or a related field
5+ years of experience in Data Engineering, ideally supporting AI or ML workloads
Strong experience with the GCP data ecosystem
Proficiency in Python and SQL, with experience in data pipeline orchestration (e.g., Airflow, Dagster, Cloud Composer)
Deep understanding of NoSQL systems (e.g., MongoDB) and vector databases (e.g., FAISS, Vector Search)
Experience designing data architectures for RAG, embeddings, or model training pipelines
Knowledge of data governance, security, and compliance for sensitive or regulated data
Familiarity with W&B / MLflow / Braintrust / DVC for experiment tracking and dataset versioning (extract snapshots, change tracking, reproducibility)
Familiarity with containerized environments (Docker, Kubernetes) and CI/CD for data workflows
A collaborative mindset and passion for building the data foundations of next-generation AI systems

Job Responsibility

Ensure high standards of data quality for AI model inputs
Design, build, and maintain scalable data pipelines on Google Cloud Platform (GCP) for AI and machine learning use cases
Implement data ingestion and transformation frameworks that power Retrieval systems and training datasets for LLMs and multimodal models
Architect and manage NoSQL and Vector Databases to store and retrieve embeddings, documents, and model inputs efficiently
Collaborate with ML and platform teams to define data schemas, partitioning strategies, and governance rules that ensure privacy, scalability, and reliability
Integrate unstructured and structured data sources (text, speech, image, documents, metadata) into unified data models ready for AI consumption
Optimize performance and cost of data pipelines using GCP native services (BigQuery, Dataflow, Pub/Sub, Cloud Storage, Vertex AI)
Contribute to data quality and lineage frameworks, ensuring AI models are trained on validated, auditable, and compliant datasets
Continuously evaluate and improve our data stack to accelerate AI experimentation and deployment

What we offer

Free comprehensive health insurance for you and your children
Parent Care Program: additional leave on top of the legal parental leave
Free mental health and coaching services through our partner Moka.care
For caregivers and workers with disabilities, a package including an adaptation of the remote policy, extra days off for medical reasons, and psychological support
Work from EU countries and the UK for up to 10 days per year, thanks to our flexibility days policy
Work Council subsidy to refund part of a sport club membership or a creative class
Up to 14 days of RTT
Lunch voucher with Swile card

Fulltime

Staff Software Engineer, Core AI

As a Staff AI Engineer on our Core AI team, you will be a cornerstone of FloQast...

Location

United States , San Jose

Salary:

164000.00 - 246000.00 USD / Year

FloQast

Expiration Date

Until further notice

Requirements

10+ years of professional software engineering experience
4+ years focused on building backend for production applications
Mastery of Python
Familiarity with some AI application frameworks, context engineering, and scalable system design for AI products
Expertise in designing products that integrate with multiple technologies, APIs, and data sources in cloud-native environments (AWS preferred)
Strong desire to develop deep hands-on experience with LLM APIs, retrieval-augmented generation (RAG), conversational AI, document processing, and MCP integrations
Proven ability to lead tech product initiatives, establish technical standards and communicate complex system designs to both technical and business stakeholders

Job Responsibility

Architect and lead development of production AI products including intelligent chatbots, document processing systems, and agentic workflows using Python and modern AI frameworks
Design and implement our centralized AI platform including model routing, provider management, vector search, and AI application frameworks with seamless MCP (Model Context Protocol) integrations
Build scalable AI products that integrate with diverse technologies including accounting systems, document repositories, and external APIs while maintaining robust monitoring and observability
Master context engineering and system design for AI applications, ensuring optimal information retrieval, context assembly, and multi-turn conversation management
Collaborate with Product, Engineering, and Security teams to ensure AI products are robust, compliant, and aligned with business objectives in the regulated accounting space
Provide technical leadership and mentorship to the growing AI team, establishing best practices for AI product development, deployment, and governance

What we offer

Medical
Dental
Vision
Family Forming benefits
Life & Disability Insurance
Unlimited Vacation

Fulltime

Platform Architect - Search & Retrieval Systems

AlphaSense

Location:
India , Bengaluru

Category:
IT - Software Development

Contract Type:
Not provided

Salary:

Job Description:

Job Responsibility:

Requirements:

Nice to have:

Additional Information:

Job Posted:
January 04, 2026

Looking for more opportunities? Search for other job offers that match your skills and interests.

Similar Jobs for Platform Architect - Search & Retrieval Systems

Principal AI Engineer

Staff Application Engineer, Workplace Technology

Staff Application Engineer, Workplace Technology

LLM Engineer

LLM Engineer

Data Scientist

Senior Data Engineer - AI Focused

Staff Software Engineer, Core AI

Platform Architect - Search & Retrieval Systems

AlphaSense

Location:India , Bengaluru

Category:IT - Software Development

Contract Type:Not provided

Salary:

Job Description:

Job Responsibility:

Requirements:

Nice to have:

Additional Information:

Job Posted:January 04, 2026

Looking for more opportunities? Search for other job offers that match your skills and interests.

Similar Jobs for Platform Architect - Search & Retrieval Systems

Principal AI Engineer

Staff Application Engineer, Workplace Technology

Staff Application Engineer, Workplace Technology

LLM Engineer

LLM Engineer

Data Scientist

Senior Data Engineer - AI Focused

Staff Software Engineer, Core AI

Location:
India , Bengaluru

Category:
IT - Software Development

Contract Type:
Not provided

Job Posted:
January 04, 2026