Anthropic

Applied Safety Research Engineer, Safeguards

Anthropic

Apply
about 2 months ago
New York, NY, USA or San Francisco, CA, USA
Mid Level / Senior
H1B Sponsor

Base Salary

$320k - $405k/yr

Responsibilities

  • Design and run experiments to improve evaluation quality.
  • Research factors impacting model safety behavior.
  • Analyze evaluation coverage to identify measurement gaps.
  • Productionize successful research into evaluation pipelines.
  • Collaborate with Policy and Enforcement on measurable evaluations.
  • Build tooling for policy experts to create evaluations.
  • Surface findings to drive model improvements.

Requirements

  • 4+ years of software engineering or ML engineering experience.
  • Proficient in Python and comfortable working across the stack.
  • Experience building and maintaining data pipelines.
  • Comfortable with data analysis and drawing insights from large datasets.
  • Experience with LLMs and understanding their capabilities and failure modes.
  • Ability to transition between prototyping and production-quality code.
  • Excited by ambiguous problems and translating them into experiments.
  • Care deeply about AI safety and desire to make a real impact.

Benefits

  • Competitive compensation and benefits.
  • Optional equity donation matching.
  • Generous vacation and parental leave.
  • Flexible working hours.
  • Collaborative office space.

Tech Stack

Python

Categories

AI & MLData Science