CrawlJobs Logo

Metadata Intelligence & RAG Systems Intern

Netherlands, Breda · Job Posted April 05, 2026
Apply Position
Job Link Share

Job Description

This 6‑month final‑year internship offers a rare opportunity to work on state-of-the-art metadata enrichment, semantic search, embeddings, and RAG (Retrieval-Augmented Generation) inside Amgen’s production ecosystem. You will translate academic techniques into practical, reproducible prototypes using Amgen’s high-quality datasets and collaborate closely with analytics teams, engineers, and domain SMEs. This assignment is ideal for students wanting to bridge academic research with industry‑ready implementation.

Job Responsibility

  • Conduct a literature review on modern metadata enrichment, semantic search, and RAG workflows
  • Compare rule-based, Transformer/LLM‑based, and hybrid extractors + retrievers
  • Build hypotheses and design evaluation frameworks
  • Implement baseline extractors
  • Build LLM prompt pipelines, embedding-based retrievers, and hybrid workflows
  • Integrate a RAG‑enabled helper tool/playbook
  • Develop a metadata extractor + embedding + retrieval pipeline using Amgen datasets
  • Build an interactive dashboard showing catalog completeness, data quality, pipeline freshness, KPI health
  • Demonstrate how improved metadata + IR methods drive measurable productivity gains

Requirements

  • Basic Python (scripts, pandas, small experiments)
  • SQL fundamentals (SELECT, JOIN, GROUP BY, window functions)
  • Experience working in notebooks (Jupyter/Colab)
  • Problem-solving mindset and ability to debug
  • Clear written & verbal communication

Nice to have

  • Exposure to ML/NLP concepts (classification, embeddings, transformers)
  • Experience with git / basic version control
  • Any prior work with vector search or embeddings
  • Experience with Databricks, SQL, Power BI (preferred)

What we offer

  • Structured mentorship (1–2 hrs/week)
  • SME access for annotation & evaluation
  • Compute resources + production environment
  • Stakeholder exposure and presentation opportunities
  • A diverse, international, collaborative environment
  • Hybrid working flexibility
  • Gym, vitality programs, healthy cafeteria
  • Possibility to apply for temporary or permanent roles

Looking for more opportunities?

Search for other job offers that match your skills and interests.

Similar Jobs for

Metadata Intelligence & RAG Systems Intern

8 matching positions

Compensation Systems Intelligence Intern

This is an 11-week paid learning experience during which you’ll be able to conne...
Location
Location
United States , Overland Park; Bellevue
Salary
Salary:
26.00 - 47.00 USD / Hour
https://www.t-mobile.com Logo
T-Mobile
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • Currently enrolled in a Bachelor’s or Master’s program in Computer Science, Data Science, Engineering, AI, or a related field
  • Strong proficiency in Python and SQL
  • Experience building applied AI systems (e.g., RAG, agentic workflows, LLM-based applications)
  • Experience in data modeling and structured pipeline design
  • Experience integrating APIs and enterprise datasets (preferred)
  • Familiarity with graph databases such as Neo4j (preferred)
  • Interest in workforce analytics, labor economics, or compensation strategy (preferred)
  • Ability to design scalable systems within enterprise constraints
  • Strong analytical and structured problem-solving skills
  • Ability to translate ambiguous business challenges into technical solutions
Job Responsibility
Job Responsibility
  • Design and prototype structured data pipelines that unify compensation data, labor market insights, and job architecture frameworks
  • Build intelligent systems leveraging Enterprise GPT and retrieval-based architectures to support compensation decision-making
  • Automate repeatable workflows such as market pricing analysis, job evaluation insights, and executive briefing preparation
  • Create orchestration frameworks that standardize compensation processes and reduce operational cycle time
  • Integrate dashboards and reporting systems to deliver scalable, executive-ready insights with improved transparency and governance
  • Build Compensation Intelligence Infrastructure: Design and implement structured data pipelines connecting compensation systems and external labor market data
  • Develop scalable data models, query frameworks, and metadata standards to enable system interoperability
  • Improve data lineage, structure, and accessibility to support AI-enabled tools and reduce manual reconciliation
  • Develop Intelligent Systems & Workflow Automation: Prototype and deploy AI-enabled systems using Enterprise GPT and retrieval-based architectures
  • Automate recurring compensation workflows to improve efficiency and consistency
What we offer
What we offer
  • Relocation assistance may be provided to program participants who reside more than 50 miles from the internship location
  • Fulltime
Read More
Arrow Right

Generative AI Architect - Wireless Standardization

We are seeking a Generative AI Architect to design, build, and deploy practical ...
Location
Location
Netherlands , Eindhoven
Salary
Salary:
7000.00 EUR / Month
https://www.randstad.com Logo
Randstad
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • Architect & Implement: Design and scale advanced GenAI solutions utilizing Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and agentic AI systems
  • Optimize & Automate: Improve, extend, and deploy internal Copilot agents and automate complex IPR (Intellectual Property Rights) lifecycle activities (e.g., generating structured summaries, metadata creation, workflow updates)
  • Advanced Prototyping: Build robust tools for intelligent document retrieval, topic identification, and automated document improvement
  • Production Governance: Evaluate solution quality, accuracy, and failure handling, ensuring robust code quality, reusable components, and documentation for long-term scalability
  • Cross-Functional Collaboration: Partner closely with wireless connectivity experts and technical domain leads who will guide prompt engineering directions and logic
  • experience: 8
  • qualifications: HBO
Job Responsibility
Job Responsibility
  • Design, build, and deploy practical GenAI solutions that augment how our engineering experts create, analyze, and utilize highly technical content and intellectual property
  • Lead the tooling, architecture, and environment setup to move advanced AI prototypes into reliable, enterprise-ready internal applications
  • Following a human-in-the-loop philosophy, your solutions will support and supercharge our domain experts rather than replace them
  • Fulltime
Read More
Arrow Right

Intermediate Site Reliability Engineer SRE – AI Reliability & Automation

At PointClickCare our mission is simple: to help providers deliver exceptional c...
Location
Location
Canada , Mississauga
Salary
Salary:
115000.00 - 128000.00 CAD / Year
pointclickcare.com Logo
PointClickCare
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • 5+ years' experience in software engineering
  • Experience with SRE principles
  • Experience with AI/ML in production environments
  • A passion for automation, intelligent systems, and operational excellence
  • Strong debugging, problem-solving, and system design skills
  • Languages: Python, Java, Bash, Terraform
  • Platforms: Azure, Kubernetes, Docker
  • Tools: Datadog, Prometheus, AppDynamics, ELK, GitHub Actions
  • ML/AI: MCP framework, AI agents, Vector store, Agent orchestration (LangChain), RAG
  • CI/CD: Jenkins, ArgoCD, Spinnaker
Job Responsibility
Job Responsibility
  • Build ML-based anomaly detection and pattern recognition systems
  • Enhance telemetry with smart tagging and metadata for better AI insights
  • Develop event-driven workflows and self-healing systems using AI triggers
  • Automate incident response with generative AI and custom AI agent orchestration
  • Use time-series forecasting and predictive modelling to anticipate failures
  • Optimise infrastructure with AI-powered autoscaling and cost-aware resource allocation
  • Build scalable, fault-tolerant systems in a cloud-native environment
  • Participate in on-call rotations and lead incident response for critical systems
  • Skilled in API integration for streamlined data exchange and system connectivity
  • Run internal AIOps workshops and help teams adopt AI maturity models
What we offer
What we offer
  • Benefits starting from Day 1!
  • Retirement Plan Matching
  • Flexible Paid Time Off
  • Wellness Support Programs and Resources
  • Parental & Caregiver Leaves
  • Fertility & Adoption Support
  • Continuous Development Support Program
  • Employee Assistance Program
  • Allyship and Inclusion Communities
  • Employee Recognition … and more!
  • Fulltime
Read More
Arrow Right

AI Engineer

Our next frontier is a strategic shift: We're evolving beyond traditional analyt...
Location
Location
United Kingdom , London
Salary
Salary:
Not provided
mvfglobal.com Logo
MVF
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • Python and service development: write clean, typed, production-ready code
  • comfortable with Pydantic, Asyncio, and FastAPI
  • treat prompts as code: versioned, tested, and decoupled from business logic
  • Cloud-native experience: hands-on experience deploying and operating containerised services on AWS (or GCP/Azure) using CI/CD platforms (Jenkins, GitHub Actions, CircleCI, BuildKite), cloud monitoring tools (Datadog, Sumologic, NewRelic), and container orchestrators (EKS, ECS)
  • comfortable with Terraform for infrastructure as code
  • Hands-on LLM experience: built something real with language models, whether production systems, serious side projects, or internal tools
  • understand that prompting is engineering, not magic
Job Responsibility
Job Responsibility
  • Architect & Engineer Agentic Systems: Build agents that act, not just answer
  • design agents that perform deterministic actions based on probabilistic reasoning
  • build systems that can reliably analyse data, execute function calls, and manage state across multi-step workflows without getting stuck in loops
  • Production-Grade RAG: go beyond basic vector search
  • implement hybrid search (keyword + semantic), re-ranking strategies, and metadata filtering
  • Structured Data Extraction: build pipelines that turn unstructured conversations into structured data that our downstream systems can use
  • Establish AI Engineering Foundations: Observability First: implement the "nervous system" of our AI
  • choose and set up tools (e.g., LangSmith, LangFuse, ADK, or custom) to trace execution chains
  • Evals as a Service: build the testing harness
  • create automated evaluation pipelines that test prompts against "Golden Datasets"
What we offer
What we offer
  • Summer Fridays
  • Competitive holiday benefits - 25 days a year paid holiday, plus 8 bank holidays (increases 1 day a year up to 30 days)
  • Hybrid working - 3 days a week in the office
  • Closed for Christmas holidays - Extra days not taken from your annual holiday allowance
  • Work from anywhere for 2 weeks a year
  • Life Assurance and Income Protection to protect your loved ones
  • Benefits allowance for health, dental, and vision coverage
  • Six months paid maternity leave, and one month paid paternity leave (subject to qualifying conditions) inclusive of same-sex and adoptive parents
  • Defined Contribution Pension and Salary Sacrifice Scheme
  • Be Well: Our award-winning wellbeing and mental health programme to support all MVFers and their families
  • Fulltime
Read More
Arrow Right

Artificial Intelligence Data Engineer II

The Artificial Intelligence Data Engineer II designs, develops, and manages scal...
Location
Location
United States , Los Angeles
Salary
Salary:
105267.00 - 173689.00 USD / Year
lacare.org Logo
L.A. Care Health Plan
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • Bachelor's Degree in Computer Science or Related Field
  • At least 5 years of experience in data engineering
  • At least 2 years of experience focused on AI/ML data pipelines
  • Hands on experience working on GenAI projects (chatbot implementations, Natural Language Processing (NLP), Sentiment Analysis, recommendation systems, anomaly detection etc.
  • Proficient skills in Python, SQL, Spark, AWS (Glue, S3, Lambda), Snowflake (Snowpark Container Services), IDMC, prompt engineering, model inference and fine-tuning, RAG and working with MCP, Vector databases
  • Proficient technical and data engineering skills
  • Solid understanding of supervised and unsupervised machine learning methods, feature engineering, model evaluation, and validation techniques
  • Ability to operationalize models in production environments, including basic MLOps practices (version control, CI/CD, reproducibility)
  • Ability to communicate complex AI/ML concepts effectively to non-technical stakeholders
  • Excellent documentation skills, ensuring reproducibility, clarity of assumptions, and transparency of model design
Job Responsibility
Job Responsibility
  • Design and implement scalable data pipelines for AI/ML workloads
  • Develop and deploy AI/ML solutions using Python, Snowpark, or cloud-native ML services
  • Build and manage feature stores to support model training and inference
  • Integrate structured and unstructured data sources from internal and external systems
  • Collaborate with data scientists to understand data requirements and optimize pipelines
  • Implement data quality checks, metadata tagging, and lineage tracking
  • Ensure compliance with Health Insurance Portability and Accountability Act (HIPAA), Centers for Medicare and Medicaid Services (CMS), and enterprise data governance standards
  • Automate data ingestion and transformation using tools like AWS Glue, Snowflake, and Informatica Data Management Cloud (IDMC)
  • Implement DevOps/MLOps and Continuous Integration (CI)/Continuous Delivery (CD) pipelines using git actions or similar tools
  • Monitor pipeline performance and troubleshoot issues in production environments
What we offer
What we offer
  • Paid Time Off (PTO)
  • Tuition Reimbursement
  • Retirement Plans
  • Medical, Dental and Vision
  • Wellness Program
  • Volunteer Time Off (VTO)
  • Fulltime
Read More
Arrow Right

Artificial Intelligence Data Engineer II

The Artificial Intelligence Data Engineer II designs, develops, and manages scal...
Location
Location
United States , Los Angeles
Salary
Salary:
105267.00 - 173689.00 USD / Year
lacare.org Logo
L.A. Care Health Plan
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • Bachelor's Degree in Computer Science or Related Field
  • At least 5 years of experience in data engineering
  • At least 2 years of experience focused on AI/ML data pipelines
  • Hands on experience working on GenAI projects (chatbot implementations, Natural Language Processing (NLP), Sentiment Analysis, recommendation systems, anomaly detection etc.
  • Proficient skills in Python, SQL, Spark, AWS (Glue, S3, Lambda), Snowflake (Snowpark Container Services), IDMC, prompt engineering, model inference and fine-tuning, RAG and working with MCP, Vector databases
  • Proficient technical and data engineering skills
  • Solid understanding of supervised and unsupervised machine learning methods, feature engineering, model evaluation, and validation techniques
  • Ability to operationalize models in production environments, including basic MLOps practices (version control, CI/CD, reproducibility)
  • Ability to communicate complex AI/ML concepts effectively to non-technical stakeholders
  • Excellent documentation skills, ensuring reproducibility, clarity of assumptions, and transparency of model design
Job Responsibility
Job Responsibility
  • Design and implement scalable data pipelines for AI/ML workloads
  • Develop and deploy AI/ML solutions using Python, Snowpark, or cloud-native ML services
  • Build and manage feature stores to support model training and inference
  • Integrate structured and unstructured data sources from internal and external systems
  • Collaborate with data scientists to understand data requirements and optimize pipelines
  • Implement data quality checks, metadata tagging, and lineage tracking
  • Ensure compliance with Health Insurance Portability and Accountability Act (HIPAA), Centers for Medicare and Medicaid Services (CMS), and enterprise data governance standards
  • Automate data ingestion and transformation using tools like AWS Glue, Snowflake, and Informatica Data Management Cloud (IDMC)
  • Implement DevOps/MLOps and Continuous Integration (CI)/Continuous Delivery (CD) pipelines using git actions or similar tools
  • Monitor pipeline performance and troubleshoot issues in production environments
What we offer
What we offer
  • Paid Time Off (PTO)
  • Tuition Reimbursement
  • Retirement Plans
  • Medical, Dental and Vision
  • Wellness Program
  • Volunteer Time Off (VTO)
  • Fulltime
Read More
Arrow Right
New

Branch Manager

Come and join us as a results driven Branch Manager to deliver sales and exceed ...
Location
Location
United Kingdom , Lymington
Salary
Salary:
Not provided
cityplumbing.co.uk Logo
City Plumbing
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • A great positive attitude
  • Enjoy customer interaction
  • Management Experience
  • Safe Practices
  • Forward Thinking
  • Tenacity and resilience
  • A pro-active approach to sales, with a strong desire and ability to win and grow new business
  • Experience of customer relationship management and developing a true partnership approach
  • Excellent communication skills
  • Self confident and self motivated, with the ability to work on own initiative or as part of a wider team
Job Responsibility
Job Responsibility
  • Effective management of the team and resource
  • Setting the standard of a sales orientated culture
  • Delivering against sales and customer demands while maximising profitability
  • Maximising margin and net profit
  • Keeping everyone safe
  • Build and maintain relationships with new and existing trade and retail customers
  • Ability to interpret and analyse financial and statistical information
What we offer
What we offer
  • Bonus
  • Discounts, savings and cash back at numerous retailers
  • Life assurance
  • Extended family policy including maternity, paternity, additional annual leave and more
  • Mental Health First Aiders and Employee Assistance Programme, we look out for each other
  • Complete induction and a company that lets you grow and encourages development
  • Financial education and loans
  • Flexible working options
  • A business striving to create an environment of inclusion so everyone can be their true self
  • Fulltime
Read More
Arrow Right
New

Guest Environment Expert

Our jobs aren’t just about giving guests a clean room and a freshly made bed. In...
Location
Location
United States , Poughkeepsie
Salary
Salary:
18.00 USD / Hour
https://www.marriott.com Logo
Marriott Bonvoy
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • Ensuring a safe work place
  • following company policies and procedures
  • maintaining confidentiality
  • upholding quality standards
  • ensuring professional uniform, personal appearance, and communications
  • ability to stand, sit, or walk for an extended time
  • ability to move, lift, carry, push, pull, and place objects weighing less than or equal to 50 pounds without assistance
Job Responsibility
Job Responsibility
  • Delivering guest requests
  • stocking carts
  • cleaning rooms and public spaces
  • maintaining the appearance and cleanliness of the whole hotel
  • Parttime
Read More
Arrow Right