Senior Full-Stack AI Engineer

Job ID: 40612998

Budget: $25 – $50 USD

I’m expanding our product with a retrieval-augmented generation (RAG) layer and need a seasoned engineer who can take an idea from proof-of-concept to a polished, production-ready service. The emphasis is on backend development, yet the role covers the full journey of building end-to-end applications so users can query large language models against our private knowledge base.

What you’ll drive
• Architect and code the RAG-powered backend: vector store integration, model orchestration, robust APIs and monitoring hooks.
• Tie everything together into a complete, reliable application that our frontend team can consume with minimal friction.
• Ship clean, well-documented code and deployment scripts so the system can be reproduced across staging and production.

Acceptance criteria
• All API endpoints return within 300 ms under our benchmark load.
• CI pipeline passes unit tests and automated linting on every merge.
• Deployment runs via a single command (Docker/Kubernetes/Terraform are welcome).

If you thrive on owning the whole stack and have recent experience turning RAG prototypes into real-world products, I’d love to see what you’ve built—links to repos or live demos are a plus.