Research Engineer, Evals - Member of Technical Staff
Callosum · London
Don’t apply blind. See how your CV matches Engineer first — free, in 30 seconds.
You will leave NewLuxJob. We do not receive or handle applications.
- Company
- Callosum
- Location
- London
- Posted
- August 20, 2026
About this job
The team tackles these problems on two fronts. We build the tools to analyse and evaluate agentic systems rigorously enough to say where and why they go wrong, and we use what we learn to design better ones. We are not simply building a better harness; the best harness will change with every new model, task and generation of silicon. We are building the layer beneath it, so that design decisions follow from evidence rather than taste. This role owns the first of those fronts. Agentic evaluation today is not up to the job: benchmarks saturate, scores move for reasons unrelated to capability, results fail to reproduce across runs, and a single number tells you nothing about which step went wrong. Every design decision the rest of the team makes rests on the quality of that instrument.…
This is a short summary.
Want to know if you're a fit? Check your CV against this role — free, in 30 seconds.
Engineer salaries in Germany
Based on 331 postings that disclose pay.
Estimated from advertised pay across our sources — indicative gross annual figures, not an offer.
Similar jobs
See if your CV fits this job
Paste your CV for an instant match score against this role — and get a tailored cover letter in one click.
- Instant match score for this role
- Tailored cover letter in one click
- Free — no credit card