AI Safety Specialist
M
MercorAI safety
Source API remote eligibility restrictions: United StatesContract
Salary24 - 35 USD per hour
Apply NowOpens the employer's application page
Job Details
- Languages
- Native fluency in English & Thai.
- Required Skills
- Cybersecurity
Requirements
- Demonstrate native fluency in English and Thai.
- Have prior red-teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
- Communicate risks clearly to technical and non-technical stakeholders.
- Adapt across projects and customers.
- Preferred: experience with adversarial machine learning, cybersecurity, and socio-technical risk.
- Preferred: skills in jailbreak datasets, prompt injection, RLHF/DPO attacks, and model extraction.
Responsibilities
- Red-team conversational AI models and agents to identify jailbreaks, prompt injections, misuse cases, and bias exploitation.
- Annotate failures, classify vulnerabilities, and flag systemic risks in human-generated data.
- Follow taxonomies, benchmarks, and playbooks to maintain consistent testing.
- Produce reports, datasets, and attack cases that customers can act on.
- Work independently and asynchronously to meet deadlines while improving AI model performance.
View Full Description & ApplyYou'll be redirected to the employer's site