Remote AI Adversarial Red Team Expert

Obsidian; San Francisco (CA); Remote; USD 120,000 - 180,000; Full time

Job summary

Mercor is seeking a remote AI red team specialist to probe and improve safety of conversational models. You will perform adversarial testing, annotate failures, and generate data to surface vulnerabilities and risks for customers.

This role emphasizes structured methodologies and clear documentation. Candidates should have red teaming or cybersecurity experience, strong English and Thai language skills, and the ability to communicate risks to both technical and non-technical stakeholders.

Qualifications

• Native fluency in English and Thai is required.
• Experience in red teaming or adversarial AI work is preferred.
• Structured thinker; uses frameworks or benchmarks.
• Strong written and verbal communication for technical and non-technical audiences.
• Ability to adapt across projects and customers.

Responsibilities

• 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

Skills

English

Thai

Tools

Adversarial ML

Cybersecurity

Socio-technical risk

Creative probing

Job description

Mercor is seeking a remote AI red team specialist to probe and improve safety of conversational models. You will perform adversarial testing, annotate failures, and generate data to surface vulnerabilities and risks for customers.

This role emphasizes structured methodologies and clear documentation. Candidates should have red teaming or cybersecurity experience, strong English and Thai language skills, and the ability to communicate risks to both technical and non-technical stakeholders.