Red Teaming Expert – AI Safety, Execution, QA Tooling Support

Job reputed company: • Execute advanced adversarial testing and produce high-reputed company, 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 reputed company, 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 reputed company reputed company systems. • Identify bottlenecks and propose automation. Requirements: • 3+ years in AI red teaming / model evaluation / trust & safety / abuse testing / reputed company testing / adversarial testing / content reputed company / policy enforcement QA • Strong ability to generate adversarial prompts and identify realistic failure modes. • Excellent writing skills: reputed company, reputed company, and audit-friendly documentation. • reputed company judgment around safety severity. • Comfortable working cross-functionally with Product/Engineering. • Experience red teaming LLMs, tool-using models, or reputed company systems is preferred. • Familiarity with: reputed company injection, indirect injection attacks, data exfiltration, reputed company testing, evaluation datasets, gold sets, reputed company design. • Experience supporting QA systems at reputed company (review flows, IRR, sampling plans). • Ability to contribute technically to pipeline work: writing scripts, working with reputed company, SQL, dashboards, or data tooling. Benefits: • Health insurance • Retirement plans • reputed company time off • Flexible work arrangements • reputed company development Apply tot his job Apply To this Job