Tech Stack

Description

You will lead the design, development, and operation of production-grade Generative AI systems, including LLM-powered applications like copilots, chatbots, and AI agents. You will architect RAG and grounded AI systems, own backend services and APIs for inference and orchestration, and drive LLMOps practices. You will also mentor engineers and influence AI strategy across teams.

Requirements

• 10+ years of professional software engineering experience
• Deep expertise in Python, FastAPI, Django, and modern backend frameworks
• Hands-on experience with LLM engineering: LangChain, LangGraph, Amazon Bedrock/OpenAI APIs, prompt engineering, RAG
• Strong experience with Elasticsearch including vector search, hybrid search, and semantic retrieval
• Proficiency with vector databases (Qdrant, ChromaDB, Pinecone) and embedding-based retrieval systems

Responsibilities

• Architect and build LLM-based applications such as copilots, chatbots, and AI agents
• Design and optimize RAG and grounded AI systems using enterprise data
• Lead development of agentic workflows with tool/function calling and multi-step reasoning
• Own backend services and APIs for AI inference and orchestration
• Drive LLMOps / GenAIOps practices (evaluation, monitoring, CI/CD, versioning)