AI Safety Experts - English & Marathi

Neon; United States; Remote; USD 120,000 - 180,000; Full time

Job summary

Mercor is seeking a remote Red Team/Data-Quality role focusing on adversarial inputs to improve AI safety. Fluency in English and Marathi is required; work involves high-sensitivity text analysis and structured testing across diverse projects.

You will annotate failures, classify vulnerabilities, and generate reproducible reports while adhering to strict guidelines. This role requires rigorous attention to detail, clear communication, and adaptability across tasks.

Qualifications

• Must have strong judgment about language and content.
• Be rigorous and notice subtle errors, inconsistencies and gaps.
• Be structured and follow guidelines and quality standards.
• Be communicative and able to explain reasoning to diverse audiences.

Responsibilities

• Red team AI models: jailbreaks, prompt injections, misuse cases, bias exploitation, multi-turn manipulation.
• Generate high-quality human data: annotate failures, classify vulnerabilities, 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.
• Ensure rigorous review to spot subtle errors, inconsistencies, and gaps.
• Follow guidelines and quality standards consistently.
• Explain reasoning clearly to technical and non-technical audiences.
• Move across projects, task types, and customers with adaptability.
• 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

Skills

Adversarial ML

Red team

Prompt injections

Model extraction

Penetration testing

Reverse engineering

Cybersecurity

Communication

Documentation

Structured testing

Job description

Location: Remote

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

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 strong judgment about language and content: you can tell whether an AI response is accurate, complete, and appropriate, and explain why
• You're rigorous: you notice subtle errors, inconsistencies, and gaps that others skim past
• You're structured: you work to guidelines and quality standards consistently, not ad hoc
• You're communicative: you explain your reasoning clearly to technical and non-technical audiences
• You're adaptable: you thrive moving across projects, task types, 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