Role Overview
The role involves acting as a specialist individual contributor executing AI red-teaming adversarial evaluation pilot, formulating risk hypotheses, and designing creative adversarial scenarios.
What You Will Do
Key responsibilities include critically evaluating model outputs, capturing and documenting evidence, submitting detailed finding cards, and collaborating with cross-functional teams.
Why It Might Be a Fit
The ideal candidate will have strong analytical, skeptical, and troubleshooting capabilities, excellent written and verbal communication skills, and a quality-focused mindset.
Requirements
- 3+ years of experience
- AI Red Teaming, Adversarial AI, Prompt Injection, Jailbreak Testing, Responsible AI, AI Governance, AI Safety
- LLM Evaluation, Model Evaluation, RLHF (Reinforcement Learning from Human Feedback), Human Feedback, Prompt Engineering, GenAI Testing, AI QA
- Strong analytical, skeptical, and troubleshooting capability
- Excellent written and verbal communication skills in US-English
- High attention to detail and structured problem-solving approach
To apply for this job please visit cnx.wd1.myworkdayjobs.com.

Follow us on social media