ML/AIWork

Gen AI Lead – RAG Specialist

Symhas · Stockton, US

Job description

Gen AI Lead – RAG (Retrieval-Augmented Generation) Specialist

We are looking for a highly skilled Gen AI Lead specializing in Retrieval-Augmented Generation (RAG) to join our AI team in Pleasanton, CA. You will own the architecture and delivery of enterprise-scale RAG systems that power intelligent search, Q&A, and knowledge management products.

Key Responsibilities

  • Design, build, and optimize end-to-end RAG pipelines for enterprise use cases
  • Lead vector store strategy, embedding model selection, and retrieval optimization
  • Implement advanced RAG patterns: hybrid search, re-ranking, contextual compression, and agentic RAG
  • Evaluate and improve answer quality, hallucination reduction, and retrieval precision
  • Guide a team of engineers in building scalable, production-grade knowledge systems
  • Partner with data engineering to ensure high-quality document ingestion pipelines

Requirements

  • 10+ years of overall AI/ML or software engineering experience
  • 3+ years building and deploying RAG systems in production
  • Expertise with vector databases (Pinecone, Weaviate, pgvector, Qdrant, etc.)
  • Strong experience with embedding models, chunking strategies, and retrieval optimization
  • Proficiency in Python, LLM APIs, and document processing pipelines
  • US Green Card or Citizenship required
  • Must be willing to work onsite in Pleasanton, CA

ML/AI Work links you to the employer's original posting — always verify the details there before applying.

More Generative AI and LLM roles

View all →
Gen AI Lead – RAG Specialist
Symhas
Apply →