AI Research Engineer, Search and Context Job at Her (SF, NYC, or Remote)

Staff AI Context Engineer

MagicSchool is seeking a Staff AI Context Engineer to architect and enhance the ...

Location

United States

Salary:

205000.00 - 240000.00 USD / Year

EdTech Jobs

Expiration Date

Until further notice

Requirements

Deep Knowledge Systems Experience: 5+ years building large-scale information systems with at least 2+ years in staff/senior roles. Extensive hands-on experience with RAG systems, knowledge graphs, or semantic search platforms in production environments.
Graph Database Expertise: Deep experience with graph databases (Neo4j, Neptune, or similar), including schema design, query optimization (Cypher, Gremlin), and building graph-based applications.
RAG & Retrieval Mastery: Demonstrated expertise building production RAG systems including embedding selection, chunking strategies, hybrid search, reranking, and retrieval evaluation. Familiarity with vector databases (pgvector, Pinecone, Weaviate, Qdrant).
Embedding & NLP Background: Strong understanding of embedding models (sentence transformers, domain-specific embeddings), fine-tuning approaches, and semantic similarity. Experience with document processing, entity extraction, and text chunking for optimal retrieval.
Technical Stack: Strong coding skills in Python and/or TypeScript/Node.js. Experience with our stack (TypeScript, Node.js, PostgreSQL, NextJS, Supabase) plus graph databases and vector stores. Familiarity with LLM APIs and context management patterns.
Information Architecture: Deep understanding of information retrieval theory, semantic search, knowledge representation, and strategies for organizing complex domain knowledge for both human and AI consumption.
Leadership & Impact: Track record of architecting complex knowledge systems, making high-leverage technical decisions about information architecture, and mentoring engineers on sophisticated retrieval and graph concepts.

Job Responsibility

Knowledge Graph & Semantic Architecture: Architect and implement graph-based knowledge systems (Neo4j, Neptune, etc) that represent educational content relationships, standards alignments, prerequisite chains, curriculum coherence, learning progressions, and pedagogical connections.
Graph Schema & Ontology Development: Design and evolve ontologies and schemas for educational content, defining entity types (standards, concepts, skills, assessments), relationship semantics, and property models.
GraphRAG Implementation: Build GraphRAG systems that combine knowledge graph traversal with vector similarity, enabling agents to retrieve contextually connected educational materials.
Retrieval Pipeline Architecture: Architect and implement sophisticated retrieval-augmented generation pipelines including hybrid search (dense + sparse), multi-stage retrieval, reranking strategies, and query understanding.
Embedding & Vectorization Strategy: Design and operationalize embedding pipelines for educational content, selecting and fine-tuning embedding models, implementing chunking strategies, and managing vector stores at scale.
Retrieval Evaluation & Optimization: Design evaluation pipelines that measure retrieval precision, recall, MRR, and NDCG across educational content types. Continuously optimize retrieval quality.
Document Ingestion & Processing: Build robust ingestion systems that process structured and unstructured educational content, extracting entities, relationships, and metadata for knowledge base population.
Semantic Parsing & Extraction: Implement NLP pipelines for educational content that extract key concepts, prerequisite relationships, learning objectives, and pedagogical metadata.
Memory & Context Management: Invent and operationalize memory compaction mechanisms, session state management, and cross-conversation memory patterns that allow agents to maintain coherence across extended teaching workflows.
Context Evaluation & Monitoring: Design evaluation frameworks that measure retrieval precision, token relevance, attention allocation, and reasoning coherence as context evolves across sessions.

What we offer

Flexibility of working from home.
Unlimited time off.
Choice of employer-paid health insurance plans. Dental and vision are also offered at very low premiums.
Generous stock options, vested over 4 years.
401k match.
Monthly wellness stipend.

Fulltime

Senior Context Engineer, AI Systems

MagicSchool is seeking a Senior Context Engineer for AI Systems to design and op...

Location

United States

Salary:

160000.00 - 190000.00 USD / Year

EdTech Jobs

Expiration Date

Until further notice

Requirements

4+ years building distributed systems
Hands-on experience with RAG systems, knowledge graphs, or semantic search platforms in production environments
Strong coding skills in Python, TypeScript/Node.js
Experience with our stack (TypeScript, Node.js, PostgreSQL, NextJS, Supabase) or similar
Proficiency with LLM APIs (OpenAI, Anthropic, etc.) and their context management patterns
Experience with Model Context Protocol (MCP), context window optimization for specific model families, or building context-aware agent frameworks
Understanding of or interest in how educational content is structured (standards, curricula, taxonomies), privacy requirements (FERPA/COPPA), and how context needs differ across teaching scenarios
Experience with agent evaluation, measuring context quality/relevance, or instrumentation for attention budget tracking

Job Responsibility

Architect and optimize how MagicSchool's AI agents reason, remember, and operate within complex educational workflows
Design context management systems that determine what information our agents see, how they maintain state across multi-turn interactions, and how they retrieve knowledge
Implement the technical foundation of how AI agents manage their 'mental workspace'
Design and implement context curation systems for product features
Build memory compaction mechanisms and state management patterns
Implement monitoring and evaluation for retrieval precision and reasoning coherence
Build dynamic, runtime data fetching that enable agents to autonomously pull relevant curriculum content, student data, and educational resources
Build token-efficient tool APIs and retrieval layers for product teams
Partner with Product to translate educational workflows into optimal context configurations
Work with evaluations researchers, platform engineers, and others to implement memory modules, retrieval adapters, and human-in-the-loop correction systems

What we offer

Unlimited time off
Choice of employer-paid health insurance plans
Dental and vision offered at very low premiums
Generous stock options, vested over 4 years
401k match
Monthly wellness stipend

Fulltime

Senior Research Engineer, LLM Evaluation and Behavioral Analysis

Together AI is building the fastest, most capable open-source-aligned LLMs and i...

Location

United States , San Francisco

Salary:

220000.00 - 270000.00 USD / Year

Together AI

Expiration Date

Until further notice

Requirements

Strong engineering skills with Python, evaluation tooling, and distributed workflows
Experience working with LLMs or transformer-based models, particularly in model evaluation, testing, or red-teaming
Ability to reason clearly about qualitative behavior, edge cases, and model failure patterns
Experience designing experiments, building datasets, and interpreting noisy behavioral signals
Understanding of function calling and structured output formats
Familiarity with GPU or distributed compute environments
Hands-on experience evaluating function-calling models, agentic systems, or tool-augmented LLM pipelines
Experience with multi-turn or multi-step reasoning tasks
Familiarity with inference systems, distributed infrastructure, or post-training workflows
Passion for discovering subtle behaviors, surprising model gaps, or edge-case failures

Job Responsibility

Build and iterate on evaluation frameworks that measure model performance across instruction following, function calling, long-context reasoning, multi-turn dialog, safety, and agentic behaviors
Develop specialized evaluation suites for: Function calling — argument correctness, schema adherence, tool selection, multi-function planning, and error recovery
Agentic workflows — task decomposition, multi-step planning, self-correction, and autonomous tool-use sequences
Tool-augmented interactions — search, retrieval, code execution, API-driven actions
Create CI/CD automated pipelines for A/B comparisons, regression detection, behavioral drift monitoring, and adversarial probing
Design and curate high-quality evaluation datasets, especially nuanced or challenging cases across domains
Collaborate with researchers and engineers to diagnose failures, triage regressions, and guide data selection, shaping strategies, objective design, and system improvements
Work with engineering teams to build dashboards, reports, and internal tools that help visualize behavior changes across releases
Operate in a fast-paced, high-impact environment with deep technical ownership and close partnership with world-class model researchers and infra engineers

What we offer

competitive compensation
startup equity
health insurance
other benefits

Fulltime

AI and Machine Learning Engineer

HPE Labs - AI and Machine Learning Engineer. This role has been designed as ‘Hyb...

Location

United States , Andover

Salary:

136500.00 - 260500.00 USD / Year

Hewlett Packard Enterprise

Expiration Date

Until further notice

Requirements

PhD in Computer Science or related fields with a focus on data engineering and data science, in particular Machine Learning, Deep Learning, and/or data management for AI
Familiarity with AI, Machine Learning and Deep Learning algorithms
Experience with Generative AI: Large Language Models, Time Series Foundation Models, Diffusion Models, etc.
Expertise with end-to-end pipelines for AI and Machine Learning and in particular the data layer underlying the pipelines (e.g., DVC, Pachyderm, Common Metadata Framework)
Experience in AI model development lifecycle, ML/deep learning frameworks and MLOps platforms (e.g. Pytorch/Tensorflow, MLFlow, Kubeflow)
Experience with agentic AI platforms (e.g., LangGraph, CrewAI, ADK, etc.)
Strong programming skills in Python, C/C++, with high proficiency in data structures and algorithms
Experience with CI/CD code development
Outstanding analytical and problem solving skills

Job Responsibility

Research and development of advanced technologies in Data-centric and Trustworthy AI, including data and knowledge context retrieval, filtering, prioritization, generative AI model materialization, advanced reasoning and validation, to improve quality of AI agentic workflows
Development of capture, management, search, enhancement and interpretation of meta-data and lineage for AI pipelines that enable reproducibility, reuse and optimization of pipelines
Discovery, selection and usage of relevant high quality data for trustworthy AI outcomes across multiple AI applications
Development, evaluation and testing of Foundation AI models for different modalities: Natural Language Processing - NLP, Large Language Models - LLM, Time Series Analysis, Computer Vision, AI for Science, etc., and augmentation of AI models with structured knowledge (i.e., knowledge infused learning)

What we offer

Health & Wellbeing
Personal & Professional Development
Unconditional Inclusion

Fulltime

Senior Software Engineer, AI

We are a leading global provider of financial information services, insights, da...

Location

United Kingdom , London

Salary:

60000.00 - 70000.00 GBP / Year

Randstad

Expiration Date

July 10, 2026

Requirements

7+ years of professional experience designing, developing, and deploying production-grade applications, with 5+ years specifically in full-stack enterprise software engineering
Advanced Python programming with strong backend development capabilities
Proven experience developing and deploying intelligent conversational AI systems using RAG architectures, Model Context Protocol (MCP), AI-enabled search, vector databases, and LLM integration
Hands-on experience building GenAI applications using LangChain and LangGraph (agent architecture design, state management, and graph-based workflow orchestration)
Solid understanding of ML algorithms, FastAPI, PyTorch/TensorFlow, MLflow, MLOps practices, containerization (Docker, Kubernetes/AWS EKS), and cloud services (AWS Bedrock, SageMaker, Azure AI Search)
Excellent communication and collaboration skills, with the ability to translate complex technical concepts for diverse, cross-functional stakeholders

Job Responsibility

Lead GenAI Development: Spearhead the creation of enterprise chatbot platforms, evaluation frameworks, agentic workflows, RAG architectures, and MCP implementations
Pioneer Innovation: Act as a hands-on engineer bridging the gap between research breakthroughs and production-ready capabilities to generate tangible business value
Build Robust Infrastructure: Develop enterprise-scale APIs (FastAPI) and architect comprehensive cloud-based AI infrastructure on AWS/Azure optimized for scalability and performance
Demonstrate Full-Stack Excellence: Apply your expertise across the entire technology stack to seamlessly integrate AI capabilities into user-facing products and backend systems

What we offer

Transformative AI Impact: Design and deploy production-ready GenAI platforms, multi-agent systems, and intelligent automation that reshape products in real-time
Cutting-Edge Tech Stack: Experiment with the latest LLMs, architect RAG implementations, design sophisticated agentic systems, and develop Model Context Protocol (MCP) servers
Enterprise Scale: Build GenAI solutions across multiple business units while creating unified patterns and reusable component frameworks
Dynamic Culture: Work at the intersection of advanced engineering and product development within a collaborative, innovation-driven environment

Fulltime

!

Senior AI Engineer

In this role you will lead a critical and highly visible function within Teradat...

Location

India , Hyderabad; Pune; Bengaluru

Salary:

Not provided

Teradata

Expiration Date

Until further notice

Requirements

5+ years of hands-on experience in backend development, distributed systems, or AI infrastructure, with a proven track record of delivering in high-scale environments
Expertise in building and deploying AI-integrated software, particularly with LLMs and frameworks like LangChain, AutoGen, CrewAI, Semantic Kernel, or custom orchestrators
Strong development skills in Python (preferred), Go, Java, or similar languages used in intelligent system design
Practical knowledge of agentic AI principles — including task decomposition, autonomous decision-making, memory/context management, and multi-agent collaboration
Experience implementing or integrating the Model Context Protocol (MCP) to facilitate standardized agent context management and interoperability across tools
Extensive experience with Cloud Service Providers (AWS, Azure, GCP) including cloud-native infrastructure, container orchestration (Docker, Kubernetes), and infrastructure-as-code tools (Terraform, Ansible)
Familiarity with vector databases (Pinecone, Weaviate, FAISS) and embedding models for semantic search and retrieval-augmented generation (RAG)
Demonstrated ability to design clean APIs, modular microservices, and resilient, maintainable backend systems
Clear communicator with the ability to simplify complex AI system behaviors into actionable architecture
Passion for AI and a hunger to build systems that push the boundaries of autonomous software

Job Responsibility

Design, develop, and scale intelligent software systems that power autonomous AI agents capable of reasoning, planning, acting, and learning in real-world environments
Lead the implementation of core Agentic AI components — including agent memory, context-aware planning, multi-step tool use, and self-reflective behavior loops
Architect robust, cloud-native backends that support high-throughput agent pipelines across major Cloud Service Providers (AWS, Azure, GCP), ensuring best-in-class observability, fault tolerance, and scalability
Build seamless integrations with large language models (LLMs) such as GPT-4, Claude, Gemini, or open-source models — using advanced techniques like function calling, dynamic prompting, and multi-agent orchestration
Design and implement standardized context management and sharing using the Model Context Protocol (MCP) to enable consistent, interoperable agent and tool interactions
Develop scalable APIs and services to connect agents with internal tools, vector databases, RAG pipelines, and external APIs
Own technical delivery of major agent-related features, leading design reviews, code quality standards, and engineering best practices
Collaborate cross-functionally with researchers, ML engineers, product managers, and UX teams to translate ideas into intelligent, performant, and production-ready systems
Define and implement testing strategies to validate agentic behavior in both deterministic and probabilistic conditions
Guide junior engineers and peers by mentoring, unblocking challenges, and championing a culture of technical excellence

What we offer

Flexible work model
Focus on well-being
Inclusive environment

Fulltime

Senior AI Engineer

As a Senior AI Engineer focused on agentic framework, you will focus on building...

Location

Denmark , København

Salary:

Not provided

Life Science Talent

Expiration Date

Until further notice

Requirements

Strong programming skills in Python and the ability to contribute to production-grade codebases
Hands-on experience in LLMs, including at least some of the following: Training, finetuning, or post-training transformer-based models
Building or operating LLM inference services in production, including performance work
Experience with embeddings, vector databases, and semantic search
Practical experience implementing RAG architectures
Designing robust evaluations for agent workflows and generative systems, including metrics, error analysis, and human evaluation methods
Experience building production-grade ML systems that can be deployed and operated, including pipelines, CI and CD practices, and monitoring
Strong product mindset with the ability to translate ideas into working systems
Clear communication and collaboration skills across research, engineering, and product
A Master’s degree in computer science, engineering, mathematics, statistics, physics, or a related field, or equivalent professional experience

Job Responsibility

Design and build LLM-powered product features used in production
Develop agentic workflows and frameworks that coordinate multiple AI components
Implement RAG architectures using embeddings and vector search
Build systems for prompting, context engineering, and tool usage
Develop evaluation frameworks to measure LLM and agent performance
Work closely with product and platform teams to turn AI capabilities into reliable, scalable product features
Continuously improve system reliability, latency, and cost efficiency of AI pipelines

What we offer

Equipment provided by Corti

Fulltime

Senior AI Engineer

Teradata is building the next generation of AI-native analytics, enabling custom...

Location

India , Hyderabad; Pune; Bangalore

Salary:

Not provided

Teradata

Expiration Date

Until further notice

Requirements

BS/MS/PhD in Computer Science, AI/ML, or a related field
3+ years of software engineering experience with a strong focus on backend systems
Hands-on experience with vector databases or vector search systems
Practical experience building LLM-powered applications, especially RAG systems
Strong understanding of embeddings and similarity search, data chunking and context optimization, dense vs sparse vs hybrid retrieval, semantic search and relevance ranking
Proficiency in Python (and/or Java)
experience with production-grade systems
Experience working with large-scale data and performance-sensitive systems.

Job Responsibility

Design and implement vector store capabilities integrated with Teradata’s analytics platform, including indexing, storage, retrieval, and query optimization
Build end-to-end RAG pipelines, including data ingestion and chunking strategies, embedding generation and lifecycle management, retrieval (dense, sparse, and hybrid search), context assembly and prompt orchestration
Develop and optimize semantic search algorithms and ranking strategies for enterprise workloads
Enable multimodal RAG (text, structured data, images, etc.) and agent-based workflows
Design agentic AI patterns, including tool calling, planning, memory, and orchestration
Implement guardrails for safety, reliability, and governance (hallucination mitigation, rounding, policy enforcement)
Build and maintain RAG evaluation frameworks, including relevance, faithfulness, accuracy, and cost metrics
Collaborate with product, research, and platform teams to translate customer use cases into scalable features
Benchmark Teradata’s vector store and RAG capabilities against industry alternatives (e.g., cloud and open-source solutions)
Contribute to technical design reviews, architecture decisions, and long-term AI platform strategy.

What we offer

People-first culture
Flexible work model
Focus on well-being
Inclusive environment.

Fulltime

Select Country

AI Research Engineer, Search and Context

Job Description

Job Responsibility

Requirements

What we offer

Looking for more opportunities?