We are hiring a Lead Generative AI Engineer to build next-generation AI-native products using LLMs, Prompt Engineering, RAG 2.0, multi-agent systems, and evaluation frameworks. This role is ideal for engineers with real-world GenAI experience building production-grade AI assistants, retrieval systems, autonomous agents, and secure AI workflows in AWS. You will work in a fast-moving Emerging Tech environment where innovation and shipping production AI systems are equally valued.
Responsibilities
Design and build GenAI applications with Agentic AI + RAG pipelines. Implement advanced Prompt Engineering patterns including chain-of-thought and self-verification. Build agent orchestration workflows with tool-augmented agents and multi-agent collaboration. Develop RAG 2.0 systems with hybrid retrieval, reranking, and citations. Create backend services using Python microservices and GenAI pipelines. Implement LLM evaluation and observability for hallucination detection and quality scoring.
Requirements
10+ years software engineering with hands-on GenAI experience. Strong Python skills. Recent production experience with Prompt Engineering, RAG pipelines, embeddings, vector search, and hallucination mitigation. Experience with LangChain, LlamaIndex, LangGraph, or similar frameworks. Proficiency with AWS services including Bedrock, SageMaker, OpenSearch, Lambda, ECS.
Experience with Java/Springboot. Familiarity with document AI services. Knowledge of LLMOps tools like LangSmith, TruLens, RAGAS, DeepEval. Experience with vector databases like FAISS, Pinecone, Weaviate, Milvus.