Red Teaming Fellowship
Core
Evaluate the safety, security, and reliability of advanced AI systems through adversarial testing and red teaming exercises.
Role type
Red Teaming Fellow (hands-on IC)
Builds
Evaluation frameworks, taxonomies, testing methodologies, and actionable security reports for frontier AI labs and platforms.
Domain
AI Safety / Cybersecurity / Adversarial Testing
Deliverable
production ML models | product features | dashboards & analysis | research | client delivery
Required skills
adversarial testing, prompt engineering, attack strategy design, vulnerability analysis, report writing, creative adversarial thinking
Preferred skills
Python, Bash, large language models, cybersecurity, research methodologies, foreign language proficiency
Technologies
Python, Bash, large language models
Responsibilities
Conduct adversarial testing across safety, security, and misuse scenarios; Design and execute red teaming exercises against models and AI applications; Develop prompts, attack strategies, and test cases; Analyze model behavior and document findings; Support development of evaluation frameworks and testing methodologies; Research emerging AI threats and attack techniques
Seniority
Fellow, hands-on IC