← Back to Talent Bench
Ref #HL-EVAL-2201Senior Level · 8 Years Experience
Ready to InterviewGenAI Red Teamer & Policy Regression Lead
Specialization: Gen AI Evaluation & Safety · Industries: Enterprise SaaS, Financial Services, Healthcare AI · Vetting Rating: Interview-ready · adversarial testing review
Contract EngagementContractor / Deployable
AvailabilityWithin 2 weeks
Work ModelRemote worldwide
Benchmark Rate~$105 / hr
Verified Technical Stack:
Red TeamingJailbreak TestingOWASP LLMGuardrailsPolicy RegressionPythonPrompt InjectionTool Abuse ScenariosCI IntegrationThreat Modelling
Professional Summary
Adversarial tester who turns repeatable jailbreak and policy-bypass findings into automated regression cases — with explicit notes on residual risk, not safety guarantees.
Verified Impact & Project Highlights
- Structured OWASP LLM-style test packs for tool-calling assistants in regulated contexts
- Converted manual red-team sessions into CI policy regression suites shared with eval engineers
- Writes findings for engineering leads without overstating coverage
Request an interview with HL-EVAL-2201
Hiring teams only. We reply within one business day with slots. Candidate names stay off this site.
Engineer looking at this profile? Do not fill the interview form.Apply to join the bench.