AI Safety Expert - Red Teaming

Obsidian; San Francisco (CA); On-site; USD 100,000 - 140,000; Full time

Job summary

Obsidian is seeking a remote AI red team expert responsible for probing AI models with adversarial inputs to uncover vulnerabilities. You will apply structured testing frameworks, document findings, and generate high-quality data to improve AI safety.

The ideal candidate brings red-teaming experience, a curious mindset, and clear communication skills to explain risks effectively. Join us to play a pivotal role in enhancing the robustness of AI systems.

Qualifications

• Prior experience in AI adversarial work including cybersecurity.
• Strong communication skills for explaining risks to stakeholders.
• Ability to structure tests using frameworks.

Responsibilities

• Red team conversational AI models and agents.
• Generate high‑quality human data through annotation and flagging.
• Document reproducibly to produce actionable reports and datasets.

Skills

Red‑teaming experience (AI adversarial work)

Curiosity and adversarial mindset

Structured approach to testing

Clear communication skills

Adaptability across projects

Job description

Location

Remote

Fluent Language Skills Required

English & Punjabi. Native fluency in both languages is required.

Why This Role Exists

At Mercor, we believe the safest AI is the one that’s already been attacked — by us. We are assembling a red team for this project – human data experts who probe AI models with adversarial inputs, surface vulnerabilities, and generate the red team data that makes AI safer for our customers.

This project involves reviewing AI outputs that touch on sensitive topics such as bias, misinformation, or harmful behaviors. All work is text‑based, and participation in higher‑sensitivity projects is optional and supported by clear guidelines and wellness resources. Before being exposed to any content, the topics will be clearly communicated.

What You’ll Do

• Red team conversational AI models and agents: jailbreaks, prompt injections, misuse cases, bias exploitation, multi‑turn manipulation
• Generate high‑quality human data: annotate failures, classify vulnerabilities, and flag systemic risks
• Apply structure: follow taxonomies, benchmarks, and playbooks to keep testing consistent
• Document reproducibly: produce reports, datasets, and attack cases customers can act on

Who You Are

• You bring prior red‑teaming experience (AI adversarial work, cybersecurity, socio‑technical probing)
• You’re curious and adversarial: you instinctively push systems to breaking points
• You’re structured: you use frameworks or benchmarks, not just random hacks
• You’re communicative: you explain risks clearly to technical and non‑technical stakeholders
• You’re adaptable: thrive on moving across projects and customers

Nice‑to‑Have Specialties

• Adversarial ML: jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction
• Cybersecurity: penetration testing, exploit development, reverse engineering
• Socio‑technical risk: harassment/disinfo probing, abuse analysis, conversational AI testing
• Creative probing: psychology, acting, writing for unconventional adversarial thinking

What Success Looks Like

• You uncover vulnerabilities automated tests miss
• You deliver reproducible artifacts that strengthen customer AI systems
• Evaluation coverage expands: more scenarios tested, fewer surprises in production
• Mercor customers trust the safety of their AI because you’ve already probed it like an adversary

Why Join Mercor

• Build experience in human data‑driven AI red teaming at the frontier of safety
• Play a direct role in making AI systems more robust, safe, and trustworthy