Role Summary
Probe advanced AI products for unsafe behavior and novel abuse paths. Test agent workflows and guardrails to identify weaknesses and support concrete safeguards. Based in San Francisco.
This published opportunity is available through Toloka AI. Review the listing carefully for the specific work arrangement and requirements.
Responsibilities
Design adversarial tests across AI product surfaces. Test agent systems, tool use, and prompt-injection risks. Simulate coordinated attack chains. Build automated assessment frameworks. Translate findings into improvements and detection metrics.
Qualifications
Penetration-testing/red-team experience; model jailbreaking and agent-workflow testing; web-security tools; custom LLM automation; novel vulnerability discoveries and public technical work; communication; relevant bachelor's degree or equivalent background.
Preferred Qualifications
Adversarial ML, guardrails, API testing, business-logic flaws, abuse prevention, or distributed-system security.
Benefits
Vacation and parental leave; optional equity donation matching.
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].