AI role · Open offer

Research Engineer — LLM evaluation at scale

Focus: Climate AI

Paris · 100-300 employees · Scale-up · GenAI: No

This listing is optimized for AI-native talent: clear skills and tools so candidates know if they fit before they apply—and so you spend less time screening mismatches.

3 skills1 tool

Apply now Find matching talent

Share this role

At a glance

How you'll work, where, and key listing dates.

Employment: Full-time
Workplace: Hybrid
Location: Cambridge, United Kingdom · Hybrid
Compensation: £90k–£115k
Experience level: Senior
Team: R&D
Benefits & perks

About this role

What the team is looking for and how this position fits.

Cambridge-adjacent R&D cell partners with product teams across Europe to institutionalise evaluation: harnesses, judge calibration, and dataset governance before models reach customers.

Hybrid; willingness to publish internal tech notes (not necessarily public papers).

What you will do

Implement reusable eval SDKs, CI adapters, and dashboards for cross-team adoption.
Design human-in-the-loop programmes with vendor management and quality SLAs.
Quantify judge reliability vs human gold sets; recommend when to block releases.
Collaborate with safety on adversarial coverage maps.
Train engineering teams on experiment hygiene and statistical power basics.

What we look for

Strong Python engineering plus stats/ML depth.
Experience shipping eval infrastructure—not one-off Kaggle-style scripts.
Excellent writing for cross-functional alignment.

Nice to have

LangSmith/Weights & Biases style tooling familiarity.
Open-source eval dataset contributions.

Skills we're hiring for

Core capabilities—LLMs, automation, analytics, product, or domain expertise.

PythonLangChainOpenAI API

Tools & stack

Platforms and products mentioned for this role (APIs, IDEs, vector DBs, CRMs, design tools, etc.).

Docker

You're a strong fit if…

You've shipped real work with AI—not only experimented in isolation.
Several listed skills or tools show up in your recent projects.
You can explain trade-offs (quality, cost, latency, safety) in plain language.

Apply

Candidate accounts only: add your headline and bio on , and optionally a CV link or PDF so recruiters see your full résumé. Then write a short pitch below—applications use your login email.

What the employer asked for

Describe a time human labels disagreed and how you resolved it.

Register, add a headline and bio, then you can attach a CV link or PDF on My account before you apply. That keeps applications tied to your profile and makes it easier for employers to review your background.

Suggested

AI talent you may also like

Profiles ranked by overlap with this role's skills and tools—handy if you're hiring for a team or comparing backup candidates.

David Cohen

Learning Engineer (LLM)

Full-time · Chicago, IL

Profile active · Apr 5

3 skills · 1 project · 1 role · 2 use cases

Built

Rubric-aligned grader
Aligns free-text answers to state standards; flags low-confidence for teacher review.
Link

Top skills

PythonOpenAI API

Similar open roles

Other listings that share skills or tools with this one—useful if you want comparable stacks or backup options.

Research Engineer — LLM evaluation at scale

AI talent you may also like

David Cohen

Similar open roles

Elena Varga

Omar El-Sayed

James Okoro

Yuki Tanaka

Senior LLM Engineer — tool use & workflows

Research Engineer — LLM evaluation & benchmarks

Staff LLM Engineer — Agents & enterprise RAG

Staff LLM Engineer — Agents & tool use

Lead PyTorch Engineer — LLM fine-tuning & distributed training