Research Engineer, Safeguards Labs

Anthropic

San Francisco, CA, USA
$350,000—$850,000 usd py
On-site
Research project leadership
Ai/ml security and integrity
Python proficiency
Safeguards Labs investigates novel safety methods to protect Claude and its users, prototyping new approaches to safe models and production safety

Job Summary

  • Safeguards Labs investigates novel safety methods to protect Claude and its users, prototyping new approaches to safe models and production safety.
  • Research engineers will define and execute the Labs research agenda, scoping projects, running experiments end-to-end, and deciding on project viability.
  • The team is built with a roughly 3:1 mix of researchers to software engineers, offering substantial latitude and high leverage on team direction.

Matching Summary

Safeguards Labs investigates novel safety methods to protect Claude and its users, prototyping new approaches to safe models and production safety.

Salary

$350,000—$850,000 USD

Skills & Requirements

Must-have

  • Research project leadership
  • AI/ML security and integrity
  • Python proficiency
  • Large dataset analysis
  • LLM operation familiarity

Nice-to-have

  • ML model training experience
  • Agentic environment evaluation
  • Trust and safety background
  • Red teaming experience
  • Research prototype transfer

Key Requirements

  • Bachelor's degree or equivalent
  • Relevant field of study
  • Correlated years of experience with job level

Work Rights

Not specified

Sponsorship: available

Tailored Resume

Cover Letter