Staff Research Engineer: Agent Evals & Post-Training (London)

Nominal

Greater London

On-site

GBP 180,000 - 220,000

Full time

5 days ago
Be an early applicant

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Benefits offered by this job

Unlimited PTO
Free meals
Dev stipend
Annual retreat
Hardware stipend
Equity terms
In-office 5 days

Job summary

Nominal in London seeks a Staff Research Engineer to own evaluation pipelines for agent evals and post-training. You will define benchmarks, build eval suites, and guide post-training workflows across air-gapped and production environments.

You’ll collaborate with hardware experts, shape measurement strategies, and drive improvements across teams. The role requires 8+ years in ML engineering or research, strong statistical rigour, and hands-on post-training experience.

Qualifications

  • 8+ years of ML engineering or research, including evals or post-training work in production.
  • Statistical rigor in eval design and interpretation.
  • Experience evaluating LLM/agent systems, including model-graded evals.

Responsibilities

  • Build eval suites for agents, MCP tool layer, and internal company agent grounded in real hardware tasks.
  • Invent benchmarks for agents operating on physical engineering data.
  • Benchmark agents against frontier models using MCP; demonstrate relative strengths.
  • Build eval infrastructure: datasets, graders, CI regression gates.
  • Convert evals into reward signals and training data; lead post-training when needed (fine-tuning, RL, distillation).
  • Set measurement strategy and model improvement guidance with hardware experts.

Skills

8+ years ML experience
Statistical rigor
LLM/agent evals
Post-training methods
ME measurement design
Technical leadership
AI coding agents tools

Tools

MCP tool
Claude Code
Cursor
Codex

Job description

Nominal in London seeks a Staff Research Engineer to own evaluation pipelines for agent evals and post-training. You will define benchmarks, build eval suites, and guide post-training workflows across air-gapped and production environments.

You’ll collaborate with hardware experts, shape measurement strategies, and drive improvements across teams. The role requires 8+ years in ML engineering or research, strong statistical rigour, and hands-on post-training experience.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Staff ML Research Engineer: Agent Evals & Post-Training
Staff ML Research Engineer: Agent Evals & Post-Training

Nominal • Greater London

Hybrid
GBP 120,000 - 160,000
Unlimited PTO and sick leave
Free lunch, snacks, and coffee
Professional Development Stipend
+4
Staff Research Engineer, Agent Evals & Post-training - UK
Staff Research Engineer, Agent Evals & Post-training - UK

Nominal • Greater London

On-site
GBP 180,000 - 220,000
Unlimited PTO
Free meals
Dev stipend
+4
AI Evaluation Engineer: Agentic Benchmarks & Production
AI Evaluation Engineer: Agentic Benchmarks & Production

Teli Labs • Greater London

On-site
GBP 90,000 - 130,000
Production AI Research Engineer
Production AI Research Engineer

Lovable • Greater London

On-site
GBP 120,000 - 180,000
AI Engineer: Evals
AI Engineer: Evals

Teli Labs • Greater London

On-site
GBP 90,000 - 130,000
Staff ML Engineer: RL for Realistic Simulations
Staff ML Engineer: RL for Realistic Simulations

Few&Far • Greater London

On-site
GBP 225,000 - 275,000
Equity
Forward Deployed Engineer | AI Agents | London
Forward Deployed Engineer | AI Agents | London

Space Executive • Greater London

Hybrid
GBP 120,000 - 150,000
Equity
Member of Technical Staff, Evaluations
Member of Technical Staff, Evaluations

Stealth - AI x Bio • Greater London

On-site
GBP 90,000 - 150,000
Staff Engineer - AI Systems Architect (London On-Site)
Staff Engineer - AI Systems Architect (London On-Site)

MLabs • Greater London

On-site
GBP 110,000 - 150,000
Private health insurance
Dental coverage
Pension scheme
+1
Research Scientist/Engineer — Evaluations at Apollo Research
Research Scientist/Engineer — Evaluations at Apollo Research

OpenDoorHub • Greater London

On-site
GBP 90,000 - 140,000
Equity