AI Engineer (Agentic AI | RAG | LLM Systems)

About this role

Build production-grade Agentic AI systems involving planning, reasoning, and tool usage while developing scalable RAG pipelines for enterprise applications. Work on multi-agent workflows and autonomous AI systems, integrating LLMs into real-world products and deploying scalable solutions on cloud platforms like AWS, Azure, or GCP. Requires strong experience in Python with frameworks like FastAPI along with hands-on expertise in LangChain or LlamaIndex and deep understanding of RAG, embeddings, and retrieval systems. Experience with vector databases such as Pinecone, Weaviate, or FAISS is expected along with proven experience building LLM-based systems in production environments. Candidates should have 4–6 years of experience in AI or backend systems with strong problem-solving skills and real-world implementation exposure.