AI Safety Expert – English, Swedish

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 ensure consistent testing practices.

• Generate reproducible reports, datasets, and attack scenarios for client use.

• Evaluate AI outputs related to sensitive issues such as bias, misinformation, and harmful behaviors.

• Broaden evaluation coverage and reveal vulnerabilities that automated tests may overlook.

• Engage in projects aimed at training and enhancing cutting-edge AI systems.

⛳️ Requirements

• Native or fluent proficiency in both English and Swedish.

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

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

• Experience with frameworks or benchmarks for systematic testing methodologies.

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

• Flexibility to adapt across various projects and clientele.

• Experience in adversarial machine learning, including but not limited to jailbreak datasets, prompt injection, RLHF/DPO attacks, or model extraction (preferred).

• Background in cybersecurity specialties such as penetration testing, exploit development, or reverse engineering (preferred).

• Familiarity with socio-technical risk assessment, including harassment/disinformation probing, abuse analysis, or conversational AI evaluation (preferred).

• Creative probing experience in fields like psychology, acting, or writing (preferred).

• Candidates must not be on an H-1B or STEM OPT visa.

🏝️ Benefits

• Fully remote position.

• Flexible work schedule allowing you to set your own hours.

• Receive weekly payments via Stripe or Wise.

• Gain valuable experience in human data-driven AI red teaming.

• Play a direct role in enhancing the robustness, safety, and trustworthiness of AI systems.

• Competitive compensation.

• Collaborate with leading researchers in the field.

• Reasonable accommodations available upon request.

• Earn referral bonuses of up to $250 for each successful referral (conditions may apply).