AI Safety Expert – English, Dutch

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

📋 Description

• Engage in red team assessments of conversational AI models and agents, utilizing techniques such as jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulation.

• Document failures, categorize vulnerabilities, and identify systemic risks.

• Adhere to established taxonomies, benchmarks, and playbooks to ensure consistent testing practices.

• Generate reproducible reports, datasets, and attack scenarios.

• Investigate sensitive topics such as bias, misinformation, and harmful behaviors.

• Provide deliverables that enhance evaluation coverage and fortify customer AI systems.

• Collaborate with top researchers on initiatives aimed at training and improving AI systems.

⛳️ Requirements

• Required native fluency in both English and Dutch.

• Previous red teaming experience in AI adversarial contexts, cybersecurity, or socio-technical investigations.

• Capability to test AI systems adversarially and push them to their limits.

• Proficient in utilizing frameworks, taxonomies, benchmarks, and playbooks for systematic testing.

• Ability to clearly communicate risks to both technical and non-technical audiences.

• Flexibility to adapt to various projects and client needs.

• Must maintain independent contractor status.

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

🏝️ Benefits

• Fully remote work environment.

• Flexible scheduling to suit your needs.

• Weekly payments processed via Stripe or Wise.

• Competitive compensation.

• Optional participation in higher-sensitivity projects.

• Comprehensive guidelines and wellness resources for projects involving sensitive content.

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