We are hiring a GenAI Engineer to join a team building and delivering real-world generative AI solutions - systems that move beyond prototypes and into production, where real users rely on them every day.
You'll take complex problems from the first customer conversation through to a working system running in their environment. You'll build GenAI solutions that are deployed, used, and relied upon - not just demos or experiments.
The problems are unusual, and the constraints are real: on-premise and air-gapped deployments, strict data handling requirements, and complex customer environments. A meaningful part of your work will happen on-site with the people who use the systems you build.
What you'll do:
Build end-to-end GenAI systems: RAG pipelines, agentic workflows, document understanding, and extraction from messy real-world data.
Own the full lifecycle - from data pipelines and model/prompt design to evaluation, deployment, monitoring, and the critical work of making systems reliable and production-ready.
Define what success looks like for each use case, measure performance, and stand behind the results.
Work directly with customers on-site, translating their needs into practical technical solutions.
Requirements: 3+ years building data or ML systems, with things you shipped that other people then used.
Strong Python and real software engineering habits - testing, version control, code you'd hand to someone else.
Hands-on experience with LLM-based systems: RAG, agents, structured extraction, or evaluation.
Comfort with production: containers, CI/CD, cloud (AWS / GCP / Azure).
Ability to explain technical work clearly to non-technical stakeholders.
Bonus: on-premise or disconnected deployment, defense or another regulated domain, classical ML depth.
This position is open to all candidates.