What you will do

The objective of this project is to design and implement a Retrieval-Augmented Generation (RAG) pipeline leveraging Large Language Models (LLMs) to enable intelligent analysis and question-answering over domain-specific text corpora.

Using tools such as LangChain, LangGraph, and AI Foundry integrated with OpenAI APIs, the solution will ingest, index, and contextualize unstructured data, providing users with accurate, explainable, and context-aware responses.

The roadmap for this project will likely be to move as much of the bespoke RAG stuff we've built to AI Foundry to make it easier to sustain.

The developer will work in collaboration with cross-functional teams within a large enterprise environment, focusing on secure, scalable, and maintainable AI solutions.

• Design and implement RAG pipelines using LLMs for intelligent document analysis and cotextual question-answering.
• Integrate RAG workflows with AI Foundry and OpenAI APIs.
• Work with LangChain and LangGraph frameworks.
• Migrate existing RAG implementations to AI Foundry.
• Ensure compliance with enterprise-level security and data protection processes.
• Continuously explore emerging AI technologies to improve model accuracy and usability.

Requirements

MUST

• Hands-on experience with LLM/NLP and RAG architecture
• Practical experience with Python
• Familiarity with LangChain and LangGraph
• WEB API experience
• Experience with AI Foundry
• Experience working in a large company, navigating complex security requirements to successfully deliver projects.
• Ability to build solutions that deliver explainable and context-aware outputs
• Team-oriented with strong communication skills

NICE TO HAVE

• Experience with OpenAI
• Familiarity with C#