Red Teaming Expert – AI Safety, Execution, QA Tooling Support
Posted 81ds ago
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
Red Teaming Expert focused on executing adversarial testing for AI safety. Partnering with Product/Engineering to enhance QA tooling and delivery pipelines.
Responsibilities:
- Execute advanced adversarial testing and produce high-quality, reproducible findings.
- Partner with Product/Engineering to improve the QA tooling and delivery pipeline.
- Design and run adversarial tests across multiple failure modes.
- Create realistic multi-turn scenarios and produce clear, reproducible findings.
- Participate in QA review cycles to improve consistency and signal.
- Help refine rubrics and evaluation standards over time.
- Collaborate with TPM + Engineering to build scalable quality systems.
- Identify bottlenecks and propose automation.
Requirements:
- 3+ years in AI red teaming / model evaluation / trust & safety / abuse testing / security testing / adversarial testing / content integrity / policy enforcement QA
- Strong ability to generate adversarial prompts and identify realistic failure modes.
- Excellent writing skills: crisp, structured, and audit-friendly documentation.
- Sound judgment around safety severity.
- Comfortable working cross-functionally with Product/Engineering.
- Experience red teaming LLMs, tool-using models, or agentic systems is preferred.
- Familiarity with: prompt injection, indirect injection attacks, data exfiltration, privacy testing, evaluation datasets, gold sets, benchmark design.
- Experience supporting QA systems at scale (review flows, IRR, sampling plans).
- Ability to contribute technically to pipeline work: writing scripts, working with APIs, SQL, dashboards, or data tooling.
Benefits:
- Health insurance
- Retirement plans
- Paid time off
- Flexible work arrangements
- Professional development















