Job Details
JPC - 1685 – Data Engineer (AI / RAG)
Posted 4 months agoPrimary Skills
Job Description
Client: FINRA
We’re looking for a hands-on AI Data Engineer to build and optimize data pipelines and retrieval systems powering next-gen Generative AI applications.
Location: Rockville (3 days onsite)
Duration: 6+ months (extension likely)
Interview: 2 rounds
Visa: UC/h4ead/h1b/gc ead
experience- 10-15
need strong RAG hands-on
What You’ll Do:
• Build scalable ETL pipelines for structured & unstructured data
• Design and optimize RAG (Retrieval-Augmented Generation) pipelines
• Work with vector search, embeddings, and retrieval tuning
• Improve search relevance, precision & recall
• Develop data validation, testing, and benchmarking frameworks
• Collaborate with AI/Agent teams for high-quality knowledge retrieval
Must-Have Skills:
• Strong Python + Data Engineering (ETL)
• Hands-on AWS (S3, Lambda, Step Functions, OpenSearch)
• Experience with RAG / Search / Retrieval systems
• Knowledge of Vector DBs / Elasticsearch / OpenSearch
• Experience handling unstructured data (PDFs, documents, logs)
Nice to Have:
• AWS Bedrock, LangChain / LlamaIndex
• Hybrid search, reranking, evaluation frameworks
• Experience in regulated environments (PII, compliance)
Ideal Candidate:
Someone who has actually built RAG pipelines end-to-end — not just traditional ETL or ML models.