Bilingual AI Safety Expert
New
M
MercorAI safety
United StatesContract
Salary17 - 25 USD per hour
Apply NowOpens the employer's application page
Job Details
- Languages
- Fluent in English and Indonesian.
- Required Skills
- Cybersecurity
Requirements
- Be fluent in English and Indonesian.
- Have prior red-teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
- Be able to explain risks clearly to technical and non-technical stakeholders.
- Preferred: experience with adversarial ML, including jailbreak datasets, prompt injection, RLHF/DPO attacks, or model extraction.
- Preferred: cybersecurity background in penetration testing, exploit development, or reverse engineering.
- Preferred: knowledge of socio-technical risk, including harassment or disinformation probing, abuse analysis, or conversational AI testing.
Responsibilities
- Red-team conversational AI models and agents for jailbreaks, prompt injections, misuse cases, and bias exploitation.
- Generate human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
- Apply taxonomies, benchmarks, and playbooks to maintain consistent testing.
- Document findings reproducibly in reports, datasets, and attack cases customers can act on.
View Full Description & ApplyYou'll be redirected to the employer's site