RAG AI Engineer

About the role

You will join the Invictus AI Insights team to build and improve a document‑intelligence platform that extracts, enriches, chunks, vectorizes and serves documents through a Retrieval‑Augmented Generation (RAG) layer. The codebase is Python‑based and runs on Azure, and you will own production features and fixes while receiving close mentorship.

Key responsibilities

• Develop and maintain the end‑to‑end document pipeline (extraction, enrichment, chunking/vectorization, indexing).
• Implement and enhance the RAG gateway that answers queries over the processed documents.
• Write, test, and ship Python services, reproduce issues, and deliver well‑scoped improvements.
• Improve pipeline accuracy, speed, and resilience.

Required profile

• 1–2 years of backend engineering experience or strong internship/project work.
• Solid Python skills, including async/await (asyncio) and understanding of concurrency vs. threading.
• Hands‑on experience with at least one cloud provider (Azure, AWS, or GCP) and a willingness to dive deep into Azure.
• Basic knowledge of large language models (tokens, context windows, embeddings) and high‑level RAG concepts.
• Strong debugging instincts, comfortable with logs and reproducible steps.
• Proficiency with Git, REST/HTTP, and JSON.
• Fluency with AI‑assisted development tools such as Claude Code or Cursor.
• Fast learner who can quickly pick up new technologies.

Required skills

• Python
• Asyncio / async‑await
• Azure (Function Apps, Service Bus, Cosmos DB, Blob Storage)
• Other cloud platforms (AWS, GCP)
• Large Language Models (LLMs), tokens, embeddings, RAG
• Git, REST, JSON
• AI‑assisted coding tools (Claude Code, Cursor)
• Optional: Azure OpenAI / GPT‑4o, Azure Document Intelligence, vector search, Azure AI Search
• Optional: Pydantic, FastAPI, pytest, GitHub Actions
• Optional: Application Insights, OpenTelemetry