AI Safety Expert - Adversarial ML

Mercor; Greater London; Remote; GBP 17,000 - 23,000; Full time

Job summary

Mercor is seeking AI Safety Experts (English & Odia) for a remote contract role. You will test and audit conversational AI models, create high-quality data, and document findings to help customers improve model behavior.

The position offers flexible hours, independent work, and the chance to influence safety testing across projects. Strong linguistic judgment and attention to detail are essential for success in this fast-paced, globally remote environment.

Qualifications

• Native English and Odia proficiency.
• Strong judgment about language and content.
• Meticulous 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, including jailbreaks, prompt injections, misuse cases and bias exploitation.
• Generate high-quality human data; annotate failures, classify vulnerabilities and flag systemic risks.
• Apply structure using taxonomies, benchmarks and playbooks for consistent testing.
• Document reproducibly; produce reports, datasets and attack cases for customers.
• Work independently and asynchronously; thrive in flexible hours while improving AI model performance.

Skills

English (native)

Odia

Judgment about language & content

Attention to detail

Structured guidelines & standards

Clear communication

Adaptability across projects

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.

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.