Profile cover
N

AI Safety Researcher

Noah Kovacs

Full-time · Job · London

About the role

We publish internally and submit to FAccT, AIES, and NeurIPS safety workshops. But unlike pure research labs, every finding we produce feeds directly into product guardrails used by our enterprise clients — banks, insurers, and healthcare providers who can't afford to deploy biased or unreliable models. You'll lead our safety evaluation workstream: designing red-teaming protocols for LLMs, building bias detection pipelines for classification models, and creating quantitative frameworks that compliance teams can actually use. The work spans both open-source and proprietary models. We need someone with research depth and product pragmatism. You'll write papers, but you'll also ship code that runs in production every day. If you've been frustrated by safety research that never leaves the lab, this is your chance to change that.

Responsibilities

  • Design red-teaming protocols for LLM deployments in regulated industries
  • Build automated bias detection and fairness evaluation pipelines
  • Develop quantitative safety frameworks for compliance teams
  • Publish research at safety-focused ML conferences
  • Partner with product to translate safety findings into deployable guardrails

Requirements

  • PhD or equivalent research experience in ML safety, fairness, or alignment
  • Published work in AI safety or responsible AI
  • Strong PyTorch skills and hands-on coding ability
  • Experience with evaluation methodologies for LLMs
  • Familiarity with regulatory frameworks (EU AI Act, NIST AI RMF)

Benefits

  • Fully remote across European and US time zones
  • Conference travel and publication support
  • Dedicated research time (20% of schedule)
  • Competitive salary with annual review

Keep exploring related roles

Use these topic pages to discover more roles in the same hiring cluster.

Job Type

Full-time

Level

Senior

Language

English

Salary Range

$130k – $160k / year

AI Expertise

AI & Machine Learning Engineers AI Product & Strategy

Skills

python pytorch reinforcement learning statistics hugging face

Ready to apply for this role?

Create a free talent account in under 2 minutes.

  • Apply to verified AI companies
  • Get AI-matched job recommendations
  • Message hiring managers directly
  • Build your public AI talent profile

Interested in this role? Create your free profile to apply.

Apply — create free profile