AI Engineer (LangGraph)

We are looking for a motivated AI Engineer to build and deploy AI agent workflows using LangGraph, LangChain, and LLM-based systems for real-world applications.

Responsibilities

Design and develop AI agent workflows using LangGraph and LangChain. Build and orchestrate multi-step, stateful LLM pipelines (agents, tools, memory). Integrate LLM APIs (OpenAI, Anthropic, etc.) into applications. Implement prompt engineering and RAG (Retrieval-Augmented Generation) pipelines. Work with vector databases (Pinecone, Chroma, FAISS, etc.) for context retrieval. Collaborate with engineering teams to deploy agents into production. Debug, test, and optimize agent performance and reliability. Document workflows, experiments, and findings.

Requirements

0-1 year of experience in AI/ML or LLM-based development (internships/projects accepted). Strong foundation in Python. Hands-on experience or strong project work with LangGraph and LangChain. Understanding of LLM concepts (prompting, embeddings, RAG, agents, tool calling). Familiarity with vector databases and embedding models. Basic understanding of APIs and backend integration. Good problem-solving and analytical skills. Ability to learn quickly and adapt to new tools/frameworks.

Nice to Have

• Experience with LangSmith for debugging/monitoring agents. Familiarity with FastAPI/Flask for serving AI applications. Exposure to cloud platforms (AWS/GCP/Azure). Knowledge of Docker and deployment basics. Contributions to open-source AI/LangGraph projects or personal portfolio.