Research Engineer / Scientist, Alignment

Anthropic
San Francisco
Workplace: HybridFull timeFunction: Research & Scientific (R&D)Education: bachelorsSkills: ["Communication","Collaboration","Problem-solving","Teamwork","Adaptability"]

Research Engineer on Alignment Science contributes to exploratory experimental research in AI safety, building and running elegant ML experiments to understand and steer the behavior of powerful AI systems. You’ll collaborate with Interpretability, Fine-Tuning, and Frontier Red Team, focusing on scalable oversight, AI control, and alignment assessments to keep models helpful, honest, and harmless as capabilities grow.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Anthropic
Anthropic
1 year ago

Research Engineer / Scientist, Alignment

✓ 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

Research Engineer on Alignment Science contributes to exploratory experimental research in AI safety, building and running elegant ML experiments to understand and steer the behavior of powerful AI systems. You’ll collaborate with Interpretability, Fine-Tuning, and Frontier Red Team, focusing on scalable oversight, AI control, and alignment assessments to keep models helpful, honest, and harmless as capabilities grow.
Location: San Francisco
Workplace: Hybrid
Employment Type: Full time
Job Function: Research & Scientific (R&D)

Key Responsibilities

  • •Design and run machine learning experiments to understand and steer alignment of powerful AI systems.
  • •Collaborate with Interpretability, Fine-Tuning, and Frontier Red Team to advance exploratory alignment research.
  • •Contribute to empirical research projects and document findings for broader research dissemination.
  • •Develop and evaluate methods for scalable oversight and model safety in adversarial/scenario-rich settings.
  • •Participate in building tooling and infrastructure to speed up alignment research (e.g., experiments, evaluation pipelines).
Travel: Low travel

Key Requirements

  • •Significant software, ML, or research engineering experience
  • •Experience contributing to empirical AI research projects
  • •Familiarity with technical AI safety research
  • •Preference for fast-moving collaborative projects over solo work
  • •Ability to pick up slack and contribute beyond exact job description
Experience:AI safetyML researchAlignment
Education:Bachelor's
Skills:CommunicationCollaborationProblem-solvingTeamworkAdaptability
Languages:English
Tech Stack:PythonKubernetesRLReinforcement LearningNLPML

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