AI Safety Expert - Adversarial ML

Mercor; New York (NY); Remote; USD 22,000 - 30,000; Full time

Job summary

Mercor is seeking AI Safety Experts to join our fully remote team. In this contract role, you will red team conversational AI models to identify jailbreaks, prompt injections, and misuse cases, and generate high-quality data by annotating failures and flagging risks.

You must be fluent in English and Marathi, with native proficiency, and capable of clear communication with both technical and non-technical audiences. You will follow taxonomies and playbooks to maintain testing quality.

Qualifications

• English and Marathi fluency with native proficiency in both languages.
• Excellent judgment about language and content accuracy.
• Strong attention to subtle errors and inconsistencies.
• Structured approach to guidelines and quality standards.
• Clear communication with technical and non-technical audiences.
• Adaptability across projects, tasks, and customers.

Responsibilities

• Red team conversational AI models and agents to identify jailbreaks and misuse cases.
• Generate high-quality human data by annotating failures and flagging systemic risks.
• Apply structure by following taxonomies, benchmarks, and playbooks for consistent testing.
• Document reproducibly by producing reports, datasets, and attack cases for customer action.

Skills

English & Marathi fluency

Attention to detail

Strong judgment

Structured approach

Clear communication

Adaptability

Adversarial ML

Cybersecurity

Socio-technical risk

Creative probing

Job description

About the job

Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include Benchmark, General Catalyst, Peter Thiel, Adam D'Angelo, Larry Summers, and Jack Dorsey.

Position

Position: AI Safety Experts — English & Marathi
Type: Contract
Compensation: $16–$22/hour
Location: Remote

Role Responsibilities

• Red team conversational AI models and agents to identify jailbreaks, prompt injections, and misuse cases.
• Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
• Apply structure by following taxonomies, benchmarks, and playbooks to maintain consistent testing.
• Document reproducibly by producing reports, datasets, and attack cases for customer action.

Qualifications

Must-Have

• Fluent Language Skills Required: English & Marathi. Native fluency in English and Marathi is required.
• Strong judgment about language and content accuracy.
• Rigorous attention to subtle errors and inconsistencies.
• Structured approach to guidelines and quality standards.
• Clear communication with technical and non-technical audiences.
• Adaptability across projects, task types, and customers.

Preferred

• 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.

Resources & Support

• For details about the interview process and platform information, please check: https://talent.docs.mercor.com/welcome
• For any help or support, reach out to: [e-mail]

PS: Our team reviews applications daily. Please complete your AI interview and application steps to be considered for this opportunity.