Python Developer (Generative AI, LangChain & LangGraph)

Quick Facts

• Role: Python Developer (Generative AI, LangChain & LangGraph)

• Location: Charlotte, NC or Irving, TX (Day 1 Hybrid – 3 days office per week)

• Interview: Face-to-face round with the client

• Note: Local candidates only; no relocation

Description

Build and deploy AI-powered applications, intelligent agents, and Retrieval-Augmented Generation (RAG) solutions using Python and LLM frameworks. Implement LangChain and LangGraph workflows (including stateful multi-agent routing and human-in-the-loop approval), design RAG pipelines with vector databases, and integrate LLM providers such as OpenAI, Azure OpenAI, Anthropic Claude, or open-source models.

Responsibilities

• Develop scalable backend applications using Python, FastAPI, and REST APIs
• Build LLM-powered applications using LangChain and LangGraph
• Design and implement RAG pipelines using document loaders, text splitters, embeddings, and vector databases
• Integrate LLMs such as OpenAI GPT, Azure OpenAI, Anthropic Claude, or open-source models
• Develop AI agents with tool calling, function calling, and multi-step reasoning workflows
• Implement stateful, multi-agent workflows using LangGraph, including conditional routing, persistence, checkpoints, and human-in-the-loop approval
• Work with vector databases such as FAISS, Chroma, Pinecone, or Weaviate
• Implement prompt engineering, structured outputs, and LLM response validation
• Integrate external APIs, databases, and enterprise knowledge sources
• Optimize latency, token consumption, reliability, and application performance
• Write unit tests, debug applications, and follow secure coding practices
• Deploy AI applications using Docker and cloud platforms such as AWS, Azure, or Google Cloud Platform

Requirements

• Strong programming skills in Python (OOP, exception handling, asynchronous programming, data structures)
• Hands-on experience with LangChain and LangGraph
• Good understanding of LLMs, transformers, tokens, embeddings, and context windows
• Practical experience building RAG applications and semantic search systems
• Experience with REST APIs and FastAPI or Flask
• Knowledge of vector databases and similarity search
• Familiarity with SQL/NoSQL databases such as PostgreSQL, MySQL, or MongoDB
• Experience with Git, debugging, testing, and software development best practices
• Bachelor’s or Master’s degree in Computer Science, Information Technology, or related field (or equivalent practical experience)

Benefits

Benefits not specified in the provided job posting.