Related skills
data analysis sql python investigations ai safety📋 Description
- Review leads and investigate model behavior for agentic/autonomous patterns risking safety
- Detect multi-step planning, capability chaining, tool use, persistence, and workarounds
- Develop signals/tracking to identify emerging agentic risk patterns
- Identify gaps in safeguards and monitoring; propose improvements
- Communicate findings to technical, policy, and leadership stakeholders
- Collaborate with others and support teammates
🎯 Requirements
- Deep expertise investigating complex adversarial or emergent system behavior (AI safety)
- Strong familiarity with SQL, Python in gov/research/tech settings
- Experience analyzing multi-step systems, automation, or agentic workflows
- 6+ years of investigations, threat analysis, or research
- Experience identifying failure modes and system-level risks in AI/software
- 2+ years building automated or scalable detection/investigation
- Experience presenting analytic work in technical/research/policy settings
🎁 Benefits
- Equal opportunity employer
- Reasonable accommodations for applicants with disabilities
- OpenAI privacy policy
Meet JobCopilot: Your Personal AI Job Hunter
Automatically Apply to Data Jobs. Just set your
preferences and Job Copilot will do the rest — finding, filtering, and applying while you focus on what matters.
Help us maintain the quality of jobs posted on Empllo!
Is this position not a remote job?
Let us know!