AI Safety Expert, English – Dutch

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

📋 Description

• Conduct red team assessments on conversational AI models and agents utilizing jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulations.

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

• Implement taxonomies, benchmarks, and playbooks to maintain consistency in testing.

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

• Examine AI outputs related to sensitive topics, including bias, misinformation, and harmful behaviors.

• Reveal vulnerabilities that automated tests may overlook.

• Broaden evaluation coverage across additional scenarios.

• Enhance customer AI systems to improve their safety, robustness, and trustworthiness.

• Collaborate with leading researchers on projects aimed at training and refining AI systems.

⛳️ Requirements

• Previous red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.

• Native proficiency in English and Dutch.

• Experience with adversarial inputs and evaluating AI models for vulnerabilities.

• Ability to utilize frameworks, taxonomies, benchmarks, or playbooks for structured testing procedures.

• Capability to articulate risks clearly to both technical and non-technical stakeholders.

• Flexibility to adapt across various projects and clients.

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

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

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

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

• Nice-to-have: creative probing experience in psychology, acting, or writing.

🏝️ Benefits

• Fully remote work.

• Flexible schedule with the option to work on your own terms.

• Weekly payments through Stripe or Wise.

• Participation in higher-sensitivity projects is optional.

• Clear guidelines and wellness resources available for higher-sensitivity projects.

• Competitive compensation.

• Opportunity to collaborate with leading researchers.

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