We are seeking a highly skilled Generative AI Engineer to design and deploy production-grade AI systems leveraging RAG pipelines, agentic AI workflows, and vector databases. You will work on building scalable, intelligent platforms that integrate LangChain/LangGraph, ADK, and modern LLM orchestration. This role requires strong backend engineering combined with hands-on AI toolchain expertise.
Responsibilities
- Architect and implement RAG pipelines with hybrid retrieval (dense + BM25), embeddings, and reranking.
- Build and optimize agentic AI workflows using LangChain/LangGraph, tool orchestration, and multi-agent systems.
- Design and manage vector storage solutions (FAISS, Pinecone, Chroma, Milvus) for high-performance retrieval.
- Integrate LLMs (OpenAI, Hugging Face, Groq, etc.) with structured tool calling, multi-turn flows, and guardrails.
- Collaborate with cross-functional teams to embed AI into enterprise workflows and backend services.
- Ensure observability, evaluation, and regression testing for AI pipelines to maintain reliability and accuracy.
- Contribute to prompt engineering, fine-tuning, and ADK-based integrations for domain-specific applications.
Required Qualifications
- 3–5+ years of experience in Python backend engineering (FastAPI, Django, Flask).
- Hands-on expertise with LangChain, LangGraph, ADK, and agentic AI orchestration.
- Strong knowledge of RAG architectures, embeddings, and vector databases.
- Experience with cloud platforms (Azure, AWS, GCP) and containerized deployments (Docker, CI/CD).
- Familiarity with LLM evaluation frameworks and guardrail techniques for safe AI execution.
- Solid understanding of SQL/NoSQL databases and scalable data pipelines.
