AI Agent Safety & Robustness Research Scientist

Scale AI; San Francisco (CA); On-site; USD 197,400 - 246,750; Full time

Benefits offered by this job

Comprehensive health coverage

Retirement benefits

Generous PTO

Learning and development stipend

Job summary

A leading AI research organization in San Francisco is seeking a Research Scientist to work on agent robustness. The role involves conducting research on AI safety, designing tests for AI agents, and developing mitigations for potential risks. Candidates should have a Ph.D. and a strong background in machine learning, with at least three years of experience in sophisticated ML problems. This full-time position offers a competitive salary and comprehensive benefits including health coverage, retirement plans, and generous PTO.

Qualifications

• 3+ years of experience addressing sophisticated ML problems.
• Experience with RL techniques like RLHF and DPO.
• Track record of published research in machine learning.

Responsibilities

• Conduct research on AI agents and safety protocols.
• Design tests for AI agents' risk factors.
• Develop mitigations for AI agents' failure modes.

Skills

Technical research collaboration

Safety and alignment in AI

Communication skills

Agent evaluation frameworks

Red-teaming and adversarial testing

Education

Ph.D. in a relevant field

Tools

SWE-bench

RLHF

DPO

Job description

A leading AI research organization in San Francisco is seeking a Research Scientist to work on agent robustness. The role involves conducting research on AI safety, designing tests for AI agents, and developing mitigations for potential risks. Candidates should have a Ph.D. and a strong background in machine learning, with at least three years of experience in sophisticated ML problems. This full-time position offers a competitive salary and comprehensive benefits including health coverage, retirement plans, and generous PTO.