Ai Safety Specialist - Fully Remote | Upto $35/Hr

Mercor; Sydney; Remote; AUD 47,000 - 69,000; Part time

Job summary

Mercor seeks AI Safety Experts to rigorously red team AI models and systems, identifying jailbreaks, prompt injections and biases. You will annotate failures, create vulnerability taxonomies, and produce actionable reports for customers.

Fluent in English and Thai, you will work remotely with clients across multiple projects and time zones. This contract role emphasizes independent, asynchronous work and clear risk communication to both technical and non-technical stakeholders.

Qualifications

• Fluent language skills: Native fluency in English and Thai.
• Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
• Ability to communicate risks clearly to technical and non-technical stakeholders.
• Adaptability to thrive on moving across projects and customers.

Responsibilities

• Red team conversational AI models and agents to identify jailbreaks, prompt injections, misuse cases, and bias exploitation.
• 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 that customers can act on.
• Work independently and asynchronously to meet deadlines while improving AI model performance.

Skills

English fluency

Thai fluency

Red teaming

AI adversarial work

Cybersecurity

Stakeholder 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

Position: AI Safety Experts — English & Thai
Type: Contract
Compensation: $24–$35/hour
Location: Remote

Role Responsibilities

• Red team conversational AI models and agents to identify jailbreaks, prompt injections, misuse cases, and bias exploitation.
• 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 that customers can act on.
• Work independently and asynchronously to meet deadlines while improving AI model performance.

Qualifications

Must-Have

• Fluent Language Skills: Native fluency in English & Thai.
• Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
• Ability to communicate risks clearly to technical and non-technical stakeholders.
• Adaptability to thrive on moving across projects and customers.

Preferred

• Experience with Adversarial ML, Cybersecurity, and Socio-technical risk.
• Skills in jailbreak datasets, prompt injection, RLHF/DPO attacks, and model extraction.