We are looking for an AI Engineer with strong experience in Retrieval-Augmented Generation (RAG) to design, build, and operate scalable GenAI backend systems. The role focuses on Python backend development, agentic AI workflows, vector search, and production-grade LLM pipelines.

Key Responsibilities

Design, develop, and maintain Python backend services using FastAPI and/or Flask, following clean architecture and best practices.

Build and expose REST APIs for GenAI capabilities including agents, retrieval, orchestration, evaluation, and observability.

Implement Agentic AI workflows using LangChain and LangGraph, including tool calling, planning, multi-step execution, and state graphs.

Develop end-to-end RAG systems: data ingestion, chunking, embeddings, retrieval, reranking, and response grounding.

Integrate and optimize vector databases such as FAISS, Pinecone, and Weaviate for semantic search and retrieval.

Work with structured data sources and warehouses including MySQL, PostgreSQL, and Snowflake.

Collaborate with product, data, and infrastructure teams to translate requirements into reliable, scalable AI systems.

Write unit and integration tests, enforce quality checks through GitHUB CI/CD, and ensure production readiness.