Engineering · Mid → Senior
You obsess over the exact instructions we give to models — and the data we retrieve for them, and the evaluations we grade them with. You know when to prompt, when to fine-tune, and when to redesign the workflow.
Location
Remote UK / Hybrid Rochdale
Type
Full-time
Salary
£70k – £105k
Team
Engineering
The Work
Production prompts and agent loops across multiple product lines.
Evaluation datasets that quantify quality per feature.
Structured-output pipelines with reliable schema conformance.
Automation to detect regressions on every prompt change.
Responsibilities
Own the quality of every LLM-facing surface you touch.
Design evaluation for both objective and subjective outputs.
Reduce token spend without hurting quality.
Share craft across the group via internal writing and reviews.
Requirements
3+ years software engineering.
Deep intuition for what LLMs can and can't do — earned in production.
Fluent in Python or TypeScript.
Rigorous about eval, not just vibes.
Right to work in the UK.
Nice to Have
Published examples of your prompt / eval work.
Experience with DSPy, Guidance, Outlines, Instructor.
Fine-tuning experience.
Stack
Where You'll Ship
Apply
Tell us why this role fits you. We read every application personally — usually within 5 working days.