Senior/Lead Generative AI Engineer - LLM

<p><p><b>Position :</b> Senior/ Lead GenAI Engineer<br/><br/><b>Experience :</b> 5 to 12 Years<br/><br/><b>Location :</b> Bangalore<br/><br/><b>Primary Skills :</b> Python, GenAI, LLM, RAG, LangGraph, AWS/ GCP/ Azure<br/><br/><b>Key Responsibilities :</b><br/><br/>- Define and own backend architecture for multi-agent systems, Agent development, and MCP-powered interoperability.<br/><br/>- Design Agentic RAG pipelines combining vector DBs and knowledge graphs with persistent memory (short-term, long-term, shared).<br/><br/>- Establish standards for MCP tool adapters, context servers, and agent protocols to ensure secure and scalable communication.<br/><br/>- Mentor the engineering team, lead reviews, and champion best practices.<br/><br/>- Build APIs and services in Python (FastAPI/Flask) for LLM integration (OpenAI, Bedrock, Azure AI, Claude).<br/><br/>- Implement LangGraph- and Autogen-based orchestration frameworks for agent collaboration.<br/><br/>- Integrate observability and guardrails (Langfuse, Aporia, OPA/Rego) to enforce compliance and responsible AI.<br/><br/>- Optimize inference workloads with batching, caching, and streaming pipelines.<br/><br/><b>Qualifications : </b><br/><br/>- 8+ years backend engineering (Python mandatory), 3+ years in GenAI/LLM-powered systems.<br/><br/>- Proven expertise in Agentic RAG, multi-agent frameworks (LangGraph, Autogen), and MCP-based agent orchestration.<br/><br/>- Experience with knowledge graphs, ontologies, memory layers, and retrieval pipelines.<br/><br/>- Deep understanding of cloud-native deployments (AWS Lambda, Kubernetes, EventBridge, RDS, S3).<br/><br/>- Prior experience leading backend/GenAI engineering teams at enterprise scale.<br/><br/>- Familiarity with pharma/life sciences compliance frameworks is a strong plus.</p><br/></p> (ref:hirist.tech)