[Expression of Interest] Research Engineer / Scientist, Alignment - London

Anthropic
London
Workplace: HybridFull timeGBP 260,000 - 370,000 annuallyFunction: Research & Scientific (R&D)Education: bachelorsSkills: ["Communication","Collaboration","Problem-solving"]

We are seeking a Research Engineer on Alignment Science to perform exploratory ML experiments focused on AI safety, collaborating with Interpretability, Fine-Tuning, and Frontier Red Team. The role combines scientific inquiry with engineering, conducting robust experiments on powerful AI systems, and contributing to safety-focused research including AI control and alignment stress-testing in a London-based team with occasional SF travel.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Anthropic
Anthropic
1 year ago

[Expression of Interest] Research Engineer / Scientist, Alignment - London

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 17 hours agoStatus: Live

Job Summary

We are seeking a Research Engineer on Alignment Science to perform exploratory ML experiments focused on AI safety, collaborating with Interpretability, Fine-Tuning, and Frontier Red Team. The role combines scientific inquiry with engineering, conducting robust experiments on powerful AI systems, and contributing to safety-focused research including AI control and alignment stress-testing in a London-based team with occasional SF travel.
Location: London
Workplace: Hybrid
Employment Type: Full time
Job Function: Research & Scientific (R&D)

Key Responsibilities

  • •Conduct and run elegant machine learning experiments to understand and steer the behavior of powerful AI systems with a focus on safety.
  • •Train language models and test safety interventions against adversarial scenarios.
  • •Run multi-agent reinforcement learning experiments to test safety techniques (e.g., AI Debate).
  • •Build tooling to efficiently evaluate the effectiveness of novel LLM-generated jailbreaks and related safety evaluations.
  • •Contribute ideas, figures, and writing to research papers, blog posts, and talks, and run experiments feeding into Anthropic’s Responsible Scaling Policy.
Travel: Low travel

Pay and Benefits

Salary: GBP 260,000 - 370,000 annually
Perks:Paid LeaveParental LeaveFlexible HoursEquity

Key Requirements

  • •Have significant software, ML, or research engineering experience.
  • •Have some experience contributing to empirical AI research projects.
  • •Have some familiarity with technical AI safety research.
  • •Prefer fast-moving collaborative projects to extensive solo efforts.
  • •Pick up slack, even if it goes outside your job description.
Experience:AI researchMachine learningNLP
Education:Bachelor's
Skills:CommunicationCollaborationProblem-solving
Languages:English
Tech Stack:PythonKubernetesLLMsRLLanguage models

Eligibility

Work Authorization:Sponsorship available.

Company Brief

Anthropic
Develops large-scale AI systems and safety research to create reliable, steerable, and interpretable AI assistants and models for commercial and research applications.
Industry: AI & Machine Learning
Company Size: Enterprise (1,001+ employees)
Growth: Scaleup
Valuation: Unicorn (USD 1B+)
Funding: Series C
Headquarters: San Francisco, United States
Founded: 2021
WebsiteLinkedIn