Full Description

Position: AI Red-Teamer — Adversarial AI Testing (Advanced); English & Japanese

Type: Hourly contract

Compensation: $50.5 per hour

Location: Remote

Commitment: 10–40 hours/week

Role Responsibilities Red team conversational AI models and agents, including jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks Apply testing structure by following taxonomies, benchmarks, and playbooks to keep evaluations consistent Produce reproducible documentation, including reports, datasets, and attack cases that customers can act on

Requirements Prior red teaming experience in areas such as AI adversarial work, cybersecurity, or socio-technical probing Native-level fluency in English and Japanese Strong adversarial mindset with the ability to push systems to their limits to uncover vulnerabilities Ability to use structured frameworks or benchmarks rather than ad-hoc testing approaches Ability to clearly communicate risks to both technical and non-technical stakeholders Ability to adapt and move across different projects and customers Experience with adversarial machine learning techniques such as jailbreak datasets, prompt injection, RLHF or DPO attacks, and model extraction Experience in cybersecurity, including penetration testing, exploit development, or reverse engineering Experience with socio-technical risk analysis, including harassment or misinformation probing, abuse analysis, and conversational AI testing Creative or unconventional adversarial thinking, such as psychology, acting, or writing for creative probing

Application Process (Takes 20 Mins) Upload resume Interview (15 min) Submit form