AI Safety Expert – English, Finnish

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

📋 Description

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

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

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

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

• Identify vulnerabilities that automated testing may overlook.

• Broaden evaluation coverage to minimize unexpected issues during production.

• Collaborate with top researchers and engage in projects aimed at training and refining AI systems.

⛳️ Requirements

• Proficient in both English and Finnish, with fluency or native-level skills required.

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

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

• Experience utilizing frameworks or benchmarks for systematic testing.

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

• Flexibility to adapt across various projects and clientele.

• Engagement as an independent contractor.

• Not eligible if you are an H1-B or STEM OPT candidate.

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

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

• Nice-to-have: experience in assessing socio-technical risks, such as harassment/disinformation probing, abuse analysis, or conversational AI testing.

• Nice-to-have: background in psychology, acting, or writing to foster unconventional adversarial thinking.

🏝️ Benefits

• Completely remote position.

• Flexible scheduling according to your preferences.

• Weekly compensation processed through Stripe or Wise.

• Access to wellness resources and clear protocols for sensitive projects.

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

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

• Competitive salary.

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