Python Developer with LangChain/ LanGraph
Charlotte, NC - Locals Needed
F2F for Final Round
We are seeking an experienced Python Developer with strong expertise in Generative AI, LangChain, and LangGraph to build, deploy, and optimize AI-powered applications. The ideal candidate will have hands-on experience developing LLM-based solutions, implementing agentic workflows, Retrieval-Augmented Generation (RAG) systems, and integrating AI applications with enterprise data sources and APIs.
Responsibilities:
Design and develop AI-powered applications using Python, LangChain, and LangGraph.
Build agentic workflows and multi-agent systems leveraging Large Language Models (LLMs).
Develop and optimize Retrieval-Augmented Generation (RAG) solutions.
Integrate LLMs such as OpenAI, Azure OpenAI, Claude, Gemini, and open-source models.
Create scalable APIs and microservices to support AI solutions.
Implement prompt engineering, tool calling, memory management, and workflow orchestration.
Integrate vector databases such as Pinecone, Chroma, Weaviate, or FAISS.
Collaborate with data scientists, ML engineers, and business stakeholders to deliver AI solutions.
Monitor, evaluate, and improve model performance, response quality, and system reliability.
Ensure security, governance, and responsible AI practices are followed.
Requirements:
Strong programming experience in Python.
Hands-on expertise with LangChain and LangGraph.
Experience building RAG (Retrieval-Augmented Generation) applications.
Knowledge of LLMs, prompt engineering, embeddings, and vector databases.
Experience with OpenAI/Azure OpenAI APIs.
Familiarity with FastAPI, Flask, or REST API development.
Experience with Pinecone, ChromaDB, Weaviate, FAISS, or Milvus.
Knowledge of AI agents, tool calling, memory, and workflow orchestration.
Experience with Git, CI/CD, Docker, and cloud platforms (AWS, Azure, or Google Cloud Platform).
Strong understanding of software engineering best practices and design patterns.
Preferred:
Experience with multi-agent frameworks and autonomous AI systems.
Knowledge of ML frameworks such as PyTorch or TensorFlow.
Experience with Kubernetes and containerized deployments.
Exposure to MLOps and AI model monitoring.
