Role Summary
Assess advanced AI systems for unsafe behavior and security weaknesses. Turn ambiguous testing goals into adversarial evaluations and actionable risk findings.
This published opportunity is available through Toloka AI. Review the listing carefully for the specific work arrangement and requirements.
Responsibilities
Plan and execute AI red-team assessments. Create adversarial prompts and attack chains. Analyze outputs for unsafe behavior. Document weaknesses and recommend mitigations. Update testing methods as threats evolve.
Qualifications
Two to five years of relevant experience; relevant degree or equivalent practice; cybersecurity and security-tool skills; Linux; Python/Bash; SIEM familiarity; analytical and communication skills.
Preferred Qualifications
Security certifications; AI/LLM testing; prompt-injection or jailbreak expertise; government or critical-infrastructure experience.
Benefits
Health, dental, vision, PTO, paid holidays, 401(k), professional-development support, and performance-based annual bonus.
What happens next
Submit your interest online to receive a reference number. The opportunity owner or review team may contact selected applicants about next steps.
For accommodation requests, contact [email protected].