About
London-based AI startup building an AI operating system for patents. The team focuses on solving deep technical challenges in retrieval, reasoning, and enterprise-grade LLM systems. Work involves modelling complex scientific language, reasoning over long documents, and deploying secure AI systems within enterprise workflows.
What you'll do
- Build and maintain scalable, reliable backend systems and user-facing product features
- Translate complex patent and workflow problems into production-ready software
- Develop secure LLM pipelines on AWS, integrating Java and Python services with retrieval and reasoning components
- Ship quickly, gather customer feedback, and iterate
- Own projects end-to-end across backend, frontend, infrastructure, and monitoring
- Improve engineering patterns and help shape technical direction
- Collaborate closely with product and customer-facing teams
What you'll need
- Strong engineering experience in Java and/or Python (backend) and/or TypeScript/React (frontend)
- Experience building and operating systems on AWS
- Understanding of secure system design in enterprise environments
- Ability to ship dependable systems end-to-end
- Strong academic background in a STEM discipline
- Beneficial: hands-on experience with LLMs, including RAG and evaluation
Shortlisted candidates will be contacted within 48 hours.
