Python Developer

Location: Richardson, TX; Tempe, AZ; Hartford, CT; Raleigh, NC. Type: Contract (C2C / W2).

About the role

We are seeking an experienced Python Developer with expertise in LangChain and LangGraph to design, develop, and deploy AI-powered applications, intelligent agents, and LLM-based solutions. The ideal candidate will have strong Python programming skills, experience integrating Large Language Models (LLMs), and hands-on knowledge of agentic AI workflows, Retrieval-Augmented Generation (RAG), and AI application development. The candidate will be responsible for building scalable backend services, implementing multi-step AI workflows, integrating external APIs and data sources, and developing reliable AI solutions for enterprise use cases.

Responsibilities

Python Development

• Design, develop, test, and maintain scalable Python applications and backend services.
• Write clean, reusable, modular, and well-documented Python code.
• Develop RESTful APIs using frameworks such as FastAPI, Flask, or Django.
• Implement asynchronous programming, exception handling, logging, and performance optimization.
• Integrate databases, external APIs, and third-party services.
• Write unit tests and integration tests using PyTest or equivalent frameworks.

LangChain Development

• Build LLM-powered applications using LangChain and its core components.
• Develop prompt templates, chains, structured outputs, and model integrations.
• Integrate LLM providers such as OpenAI, Anthropic, or AWS Bedrock.
• Implement Retrieval-Augmented Generation (RAG) pipelines for enterprise knowledge retrieval.
• Integrate vector databases and embedding models for semantic search.
• Implement tool calling, memory or conversation-state management, and document processing.
• Evaluate LLM responses for accuracy, relevance, latency, and reliability.

LangGraph and Agentic AI

• Design and implement stateful, multi-step AI workflows using LangGraph.
• Build AI agents that can make decisions, call tools, and execute conditional workflows.
• Implement graph-based orchestration using nodes, edges, state management, and conditional routing.
• Develop multi-agent workflows where multiple specialized agents collaborate on complex tasks.
• Implement checkpoints, persistence, human-in-the-loop approval, and workflow recovery.
• Handle retries, error states, loops, and failure recovery in agentic workflows.
• Monitor agent execution and optimize workflow performance.

LLM Integration and RAG

• Develop RAG applications using document ingestion, chunking, embeddings, retrieval, and response generation.
• Integrate vector databases such as Pinecone, Chroma, Weaviate, or FAISS.
• Implement semantic search, metadata filtering, reranking, and context optimization.
• Connect AI applications to enterprise documents, databases, and knowledge bases.
• Reduce hallucinations through retrieval grounding, validation, and appropriate guardrails.
• Implement prompt injection defenses and access controls for retrieved information.