Artificial Intelligence Researcher | Remote

About the role

Probe frontier AI models to identify vulnerabilities and failure modes.

Responsibilities

• Design challenging tasks that expose model weaknesses.
• Document findings with clear, reproducible evidence.
• Collaborate with task authors to strengthen benchmark tasks.
• Share insights with researchers to improve benchmarks.

Qualifications

• MSc or PhD in a STEM field or equivalent practical experience.
• Have strong relevant experience in research, security, or AI evaluation roles.
• Demonstrated ability to identify vulnerabilities in LLMs or ML systems.
• Proficiency in Python and Git for scripting probes and analyses.
• Familiarity with LLM capabilities, limitations, and evaluation techniques.