Role description
Experience: 5–8 Years
Employment Type: Full-time
Job Summary
We are looking for an experienced AI Agent Developer with strong expertise in building, deploying, and monitoring AI agents using the LangChain ecosystem. The ideal candidate should have hands-on experience in developing agentic AI applications, implementing orchestration workflows, evaluating LLM performance, and deploying production-ready AI solutions. The role requires proficiency in Python, Databricks, SQL, and up-to-date AI agent frameworks such as LangChain, LangGraph, and LangSmith.
Key Responsibilities
- Design, develop, and deploy AI agents using LangChain and LangGraph.
- Build stateful, multi-agent workflows with memory, tool integration, and human-in-the-loop capabilities.
- Develop Retrieval-Augmented Generation (RAG) pipelines and integrate vector databases and embeddings.
- Utilize LangSmith for tracing, debugging, observability, automated testing, and evaluation of AI agents.
- Create evaluation datasets and implement automated testing frameworks to measure LLM performance and reduce regressions.
- Optimize prompts, reasoning workflows, and agent performance through continuous experimentation and monitoring.
- Deploy, monitor, and maintain AI agents in production environments.
- Build dashboards and s to monitor latency, cost, response quality, and hallucination rates.
- Collaborate with cross-functional teams to integrate AI agents into enterprise applications.
- Follow best practices for AI application development, testing, deployment, and monitoring.
Mandatory Skills
- 5+ years of software engineering experience, including 2+ years of hands-on experience in LLM/Generative AI application development.
- Strong proficiency in Python.
- Hands-on experience with LangChain for building and deploying AI agents.
- Strong expertise in LangGraph for developing multi-agent orchestration workflows.
- Experience with LangSmith for observability, tracing, debugging, evaluations, and
📌 Lead AI Agent Developer (Kolkata)
🏢 UST
📍 Kolkata