AI Safety Specialist, English, Norwegian

This is a fully remote position, open to applicants in New York.

📋 Description

• Perform adversarial testing on conversational AI models and agents.

• Design jailbreaks, prompt-injection scenarios, misuse cases, and multi-turn manipulation tactics.

• Examine models for vulnerabilities in various conversational and adversarial contexts.

• Detect and categorize model failures and safety vulnerabilities.

• Analyze bias, misinformation, misuse, and potentially dangerous model behaviors.

• Evaluate the severity, reproducibility, and practical implications of vulnerabilities.

• Generate and annotate human evaluation data from red teaming exercises.

• Develop structured attack cases and assessment materials.

• Document adversarial scenarios, testing methodologies, model behaviors, and failure patterns.

• Create reports, datasets, and organized findings for technical teams.

• Communicate identified risks to both technical and non-technical stakeholders.

• Support broader evaluation efforts across different models and use cases.

⛳️ Requirements

• Native-level proficiency in both English and Norwegian.

• Prior experience in AI red teaming, adversarial AI assessment, cybersecurity, or socio-technical system testing.

• Strong grasp of conversational AI systems and their failure modes.

• Experience in developing structured adversarial tests.

• Capability to identify subtle vulnerabilities and recurring behavioral patterns.

• Excellent analytical reasoning and written communication abilities.

• Proficient in documenting findings clearly and reproducibly.

• Comfortable working across varying projects, scenarios, and evaluation frameworks.

• Equivalent professional experience in AI safety, adversarial testing, security, or structured model evaluation may be accepted.

• Practical experience in red teaming is especially valuable.

• Familiarity with adversarial machine learning concepts.

• Knowledge of RLHF, DPO, model extraction, or related AI training and evaluation concepts.

• Cybersecurity experience in penetration testing, exploit development, or reverse engineering.

• Experience analyzing abuse, harassment, misinformation, or other socio-technical risks.

• Background in testing conversational AI systems.

• Previous experience in generating structured human data for AI evaluation.

🏝️ Benefits

• Fully remote work environment.

• Flexible scheduling options.

• Competitive hourly pay.

• Weekly payments via Stripe or Wise.

• Optional participation in higher-sensitivity projects.

• Flexible remote consulting opportunities.

• Project timelines may be extended, shortened, or adjusted based on scope and performance.