AI Red Team – GenAI Adversarial Evaluation
Core
Design and scale adversarial evaluation systems for LLM and AI systems, focusing on indirect prompt injection, jailbreaks, and agent manipulation.
Role type
Senior IC AI security researcher (red teaming)
Builds
Scalable systems to generate and test adversarial attacks at large scale
Domain
AI security / LLM safety
Deliverable
production ML models
Required skills
LLMs, prompt injection, AI security, red teaming, security research, adversarial testing, Python, automation, creative problem-solving
Preferred skills
Offensive cybersecurity certifications (OSWA, OSWE, OSCE3, SEC542, SEC522)
Technologies
Python
Responsibilities
Create novel adversarial attacks; Build scalable systems to generate and test attacks; Review attack quality, effectiveness, novelty, and reproducibility; Identify new attack patterns and model vulnerabilities; Develop adversarial datasets, benchmarks, and regression tests; Share findings with Data Science, Security, and Engineering teams; Improve model robustness and defensive capabilities
Seniority
Senior, hands-on IC
