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 procedures.

• Generate reproducible reports, datasets, and attack scenarios.

• Investigate sensitive AI outputs related to bias, misinformation, and harmful behaviors.

• Discover vulnerabilities overlooked by automated testing methods.

• Broaden evaluation coverage and minimize unexpected production issues.

• Enhance customer AI systems, contributing to the development of safer and more reliable AI.

• Collaborate with top researchers on projects focused on training and improving AI systems.

⛳️ Requirements

• Fluency in both English and Danish is mandatory.

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

• Capability to adversarially probe AI systems.

• Familiarity with frameworks or benchmarks for structured testing methodologies.

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

• Adaptability to various projects and client needs.

• Must be an independent contractor.

• Not eligible for H1-B or STEM OPT support.

• Preferred qualifications include: adversarial machine learning, jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction, penetration testing, exploit development, reverse engineering, probing harassment/disinformation, abuse analysis, conversational AI testing, psychology, acting, or writing skills.