AI Safety Expert - Adversarial ML

mercor; United States; Remote; USD 22,000 - 30,000; Full time

Job summary

Mercor is seeking AI Safety Experts fluent in English and Odia to test and harden conversational AI systems. This remote contract role focuses on red-teaming models, identifying jailbreaks, prompt injections, and misuse cases to improve safety.

You will generate high-quality human data, annotate failures, and document reproducible attack reports for clients. Flexible hours and asynchronous work fit well with diverse time zones while maintaining rigorous quality standards.

Qualifications

• Native fluency in English and Odia.
• Strong judgment about language and content.
• Rigorous attention to detail and consistency.
• Structured approach to guidelines and quality standards.
• Clear communication with technical and non-technical audiences.
• Adaptability across projects, task types, and customers.

Responsibilities

• Red team conversational AI models and agents. Conduct jailbreaks, prompt injections, misuse cases, and bias exploitation.
• Generate high-quality human data. Annotate failures, classify vulnerabilities, and flag systemic risks.
• Apply structure. Follow taxonomies, benchmarks, and playbooks to ensure consistent testing.
• Document reproducibly. Produce reports, datasets, and attack cases that customers can act on.
• Work independently and asynchronously. Thrive in flexible hours while improving AI model performance.

Skills

English and Odia fluency

Language judgment

Attention to detail

Structured guidelines

Clear communication

Adaptability

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

AI Safety Experts — English & Odia

Type

Contract

Compensation

$16–$22/hour

Location

Remote

Role Responsibilities

• Red team conversational AI models and agents. Conduct jailbreaks, prompt injections, misuse cases, and bias exploitation.
• Generate high-quality human data. Annotate failures, classify vulnerabilities, and flag systemic risks.
• Apply structure. Follow taxonomies, benchmarks, and playbooks to ensure consistent testing.
• Document reproducibly. Produce reports, datasets, and attack cases that customers can act on.
• Work independently and asynchronously . Thrive in flexible hours while improving AI model performance .

Qualifications – Must-Have

• Native fluency in English and Odia .
• Strong judgment about language and content.
• Rigorous attention to detail and consistency.
• Structured approach to guidelines and quality standards.
• Clear communication with technical and non-technical audiences.
• Adaptability across projects, task types, and customers.

Qualifications – Preferred

• Experience in Adversarial ML : jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction.
• Background in Cybersecurity : penetration testing, exploit development, reverse engineering.
• Knowledge of socio-technical risk: harassment/disinfo probing, abuse analysis, conversational AI testing.
• Creative probing skills: psychology, acting, writing for unconventional adversarial thinking.