Job Description

Location: Remote

n

Fluent Language Skills Required: English & Odia. Native fluency in English and Odia is required for this position.

n

Why This Role Exists

n

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.

n

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.

n

What You'll Do

n

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

n

Who You Are

n

n
- You bring strong judgment about language and content: you can tell whether an AI response is accurate, complete, and appropriate,



and explain why
n
- You're rigorous: you notice subtle errors, inconsistencies, and gaps that others skim past
n
- You're structured: you work to guidelines and quality standards consistently, not ad hoc
n
- You're communicative: you explain your reasoning clearly to technical and non-technical audiences
n
- You're adaptable: you thrive moving across projects, task types, and customers
n

n

Nice-to-Have Specialties

n

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

n

What Success Looks Like

n

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

n

Why Join Mercor

n

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

📌 AI Safety Expert - Adversarial ML (Victoria)
🏢 Mercor
📍 Victoria