AI Safety Expert - Adversarial ML

mercor; Singapore; Remote; SGD 28,000 - 39,000; Full time

Job summary

Mercor, a remote-first company, seeks AI Safety Experts fluent in English and Tamil to rigorously test conversational AI models. You will generate high-quality human data, annotate vulnerabilities, and apply structured taxonomies to drive safer AI systems.

Work independently across projects and communicate findings clearly to technical and non-technical teams. Ideal candidates bring experience in adversarial ML, cybersecurity, and socio-technical risk assessment, with creative probing skills to

Qualifications

• Must be fluent in English and Tamil; native fluency in both is required.
• Strong judgment on language accuracy, completeness, and appropriateness.
• Rigorous attention to subtle errors, gaps, and inconsistencies.
• Structured, guideline-driven work with quality standards.
• Clear communication with technical and non-technical audiences.
• Adaptive across projects, task types, and customers.

Responsibilities

• Red team conversational AI models through jailbreaks, prompt injections, and misuse cases.
• Annotate failures and classify vulnerabilities to generate high-quality data.
• Apply taxonomies, benchmarks, and playbooks for consistent testing.
• Document reports, datasets, and attack cases for customers.
• Work independently and asynchronously to meet deadlines while improving AI model performance.

Skills

English

Tamil

Attention to detail

Structured approach

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: AI Safety Experts - English & Tamil

Type: Contract Compensation: $16-$22/hour

Location: Remote

Responsibilities

• Red team conversational AI models and agents through jailbreaks, prompt injections, and misuse cases. Identify bias exploitation and multi-turn manipulation.
• Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
• Apply structure by following taxonomies, benchmarks, and playbooks to ensure 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 Required: English & Tamil. Native fluency in English and Tamil is required.
  • Strong judgment about language and content accuracy, completeness, and appropriateness.
  • Rigorous attention to subtle errors, inconsistencies, and gaps.
  • Structured approach to work, adhering to guidelines and quality standards.
  • Clear communication with both 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.
  • Cybersecurity skills: 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.