Sr Gen AI Lead in Location – San Jose, CA Onsite

Technology Stack (Priority Order)
1.                  Languages: Python
2.                  Agent & RAG Frameworks: LangChain, LlamaIndex, DSPy
3.                  LLM APIs: Gemini, Bedrock, Vertex AI, Claude 
4.                  Vector DBs: Pinecone, Weaviate (Can be any )
5.                  Evaluation: LangSmith, custom eval pipelines
Key Responsibilities
·                Build multi-step and multi-agent workflows
·                Implement RAG pipelines and document retrieval strategies
· Design prompt templates, system instructions, and guardrails · Integrate agents with tools, APIs, and internal services · Optimize latency, accuracy, and token usage · Create automated LLM evaluation and regression tests
Required Skills
·                Strong Python development skills
·                Hands-on experience with LLMs and embeddings
·                Solid understanding of prompt engineering and hallucination mitigation
·                Familiarity with cloud AI services