AI Safety Expert, English – Vietnamese

This is a fully remote position, open to applicants in United States.

📋 Description

• Engage in red-teaming for conversational AI models and agents by executing jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulation.

• Generate human data through annotating failures, categorizing vulnerabilities, and identifying systemic risks.

• Utilize taxonomies, benchmarks, and playbooks to ensure consistent testing processes.

• Create reproducible reports, datasets, and attack scenarios for our clients.

• Evaluate AI outputs that involve sensitive subjects like bias, misinformation, or harmful conduct.

• Identify vulnerabilities that automated testing may overlook.

• Increase evaluation coverage while minimizing unexpected issues in production.

• Assist Mercor clients in enhancing the safety and reliability of their AI systems.

⛳️ Requirements

• Native fluency in both English and Vietnamese is a must.

• Prior experience in red teaming within AI adversarial contexts, cybersecurity, or socio-technical probing is essential.

• Capability to probe systems in an adversarial manner and test their limits.

• Familiarity with frameworks or benchmarks for systematic testing.

• Proficiency in articulating risks to both technical and non-technical audiences.

• Flexibility to adapt across various projects and clients.

• Independent contractor status is required.

• Candidates must not hold H1-B or STEM OPT status.

• Nice-to-have: experience in adversarial machine learning, including knowledge of jailbreak datasets, prompt injection, RLHF/DPO attacks, or model extraction.

• Nice-to-have: background in cybersecurity encompassing penetration testing, exploit development, or reverse engineering.

• Nice-to-have: experience in socio-technical risk management, including harassment/disinformation probing, abuse analysis, or testing of conversational AI.

• Nice-to-have: experience in psychology, acting, or writing that fosters unconventional adversarial thinking.

🏝️ Benefits

• Fully remote position that allows for flexible scheduling.

• Receive weekly payments through Stripe or Wise based on services provided.

• Project timelines may be extended, shortened, or concluded early based on requirements and performance.

• Access to wellness resources and comprehensive guidelines for projects of higher sensitivity.

• Opportunity to gain experience in human data-driven AI red teaming.

• Direct involvement in enhancing the robustness, safety, and trustworthiness of AI systems.

• Competitive compensation package.

• Referral bonuses of up to $100 for each successful referral.