Research Scientist, Ai Controls And Monitoring

Scale

San Francisco, CA, US
Base: $216,000 - $270,000 usd; equity: included ba...
On-site
Research experience in machine learning
Published research in generative ai
Experience with ai control experiments
The role focuses on designing methods to ensure advanced AI models remain aligned with intended goals in adversarial environments

Job Summary

  • The role focuses on designing methods to ensure advanced AI models remain aligned with intended goals in adversarial environments.
  • Candidates will develop real-time monitoring techniques and layered control mechanisms like fail-safes and intervention protocols.
  • The position offers a competitive compensation package including base salary, equity, comprehensive health benefits, and a learning stipend.

Matching Summary

The role focuses on designing methods to ensure advanced AI models remain aligned with intended goals in adversarial environments.

Salary

Base: $216,000 - $270,000 USD; Equity: Included based on approval; Benefits: Health, dental, vision, retirement, PTO

Skills & Requirements

Must-have

  • Research experience in machine learning
  • Published research in generative AI
  • Experience with AI control experiments
  • Three years of sophisticated ML problem solving
  • Ability to prototype new research ideas

Nice-to-have

  • Runtime monitoring and anomaly detection
  • Familiarity with scalable oversight techniques
  • Experience with RLHF and post-training methods
  • Collaboration with policymakers and engineers

Key Requirements

  • At least three years of ML experience
  • Track record of published research
  • Strong written and verbal communication skills

Work Rights

Not specified

Tailored Resume

Cover Letter