AI Safety Expert, English, Dutch

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

📋 Description

• Conduct red teaming on conversational AI models and agents by exploring jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulation.

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

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

• Generate reproducible reports, datasets, and attack scenarios for clients.

• Analyze AI outputs related to sensitive issues like bias, misinformation, or harmful behaviors.

• Identify vulnerabilities that automated testing may overlook.

• Broaden evaluation coverage and minimize unexpected outcomes in production.

• Assist Mercor clients in enhancing the safety, robustness, and trustworthiness of their AI systems.

⛳️ Requirements

• Native fluency in both English and Dutch is essential.

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

• Capability to probe systems adversarially and push them to their limits.

• Experience with frameworks or benchmarks for structured testing is necessary.

• Proficient in articulating risks to both technical and non-technical stakeholders.

• Flexibility to adapt to various projects and clients.

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

• Nice-to-have: Experience in cybersecurity, such as penetration testing, exploit development, or reverse engineering.

• Nice-to-have: Experience with socio-technical risks, including harassment/disinformation probing, abuse analysis, or testing conversational AI.

• Nice-to-have: Creative probing experience in fields like psychology, acting, or writing.

• Must be engaged as an independent contractor.

• H1-B and STEM OPT candidates are not supported.

🏝️ Benefits

• Fully remote position.

• Flexible work schedule.

• Weekly payments via Stripe or Wise based on delivered services.

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

• Participation in higher-sensitivity projects is optional.

• Clear guidelines and wellness resources available for handling sensitive content.

• Competitive compensation.

• Referral bonus of up to $250 for each successful referral.