AI Platform Engineer

About the role

We are building an AI‑powered knowledge platform that aggregates data from code repositories, documentation, and project tools to provide source‑grounded answers for requirements, code analysis, and AI‑assisted development. You will own the end‑to‑end platform, from ingestion pipelines to the full‑stack application.

Key responsibilities

• Design and implement a unified, incremental ingestion pipeline using APIs, webhooks, and connectors with parsing, normalization, deduplication, and metadata extraction.
• Create multi‑source RAG workflows including chunking, embeddings, indexing, hybrid retrieval, reranking, and context assembly.
• Enable AI understanding of large codebases, generating architecture documentation automatically.
• Develop Python (FastAPI) backend services and JavaScript/Node.js front‑ends for search, intake, and visualization.
• Enforce permission‑aware retrieval, provenance, and auditability, and apply TDD, automated testing and CI/CD via Azure DevOps.

Required profile

• 5+ years of strong Python and backend development experience.
• Hands‑on experience building LLM applications and RAG pipelines.
• Experience with data ingestion, REST APIs, webhooks and third‑party integrations.
• Full‑stack development skills with JavaScript/Node.js.
• Solid understanding of authentication, authorization and secure data access.

Required skills

• Python, FastAPI, Pydantic
• LangChain or LlamaIndex
• Vector databases such as Pinecone, ChromaDB, FAISS
• AST parsing, symbol indexing, dependency graphs
• Docker, cloud infrastructure, observability
• Azure DevOps, Git workflows, CI/CD
• JavaScript, Node.js