AI Safety Expert – English, Danish

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

📋 Description

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

• Generate human data by annotating errors, classifying vulnerabilities, and identifying systemic risks.

• Utilize taxonomies, benchmarks, and playbooks to ensure consistency in testing.

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

• Detect vulnerabilities that automated testing may overlook.

• Broaden evaluation coverage and mitigate unexpected issues in production.

• Assist clients in enhancing the safety, robustness, and reliability of AI systems.

• Engage in projects aimed at training and improving advanced AI systems.

⛳️ Requirements

• Proficient in both English and Danish is essential.

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

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

• Familiarity with frameworks or benchmarks for systematic testing is required.

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

• Versatile and able to adapt across 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: background in cybersecurity, encompassing penetration testing, exploit development, or reverse engineering.

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

• Nice-to-have: expertise in psychology, acting, or writing for unconventional adversarial approaches.

• Must be an independent contractor.

• Applicants must not require H1-B or STEM OPT sponsorship.

🏝️ Benefits

• Fully remote position.

• Flexible working hours; complete tasks on your own timetable.

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

• Project durations may vary based on requirements and performance.

• Involvement in higher-sensitivity projects is optional.

• Access to clear guidelines and wellness resources for handling sensitive content.

• Competitive compensation.

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