AI Safety Expert - Red Team

Role Responsibilities

• Red team conversational AI models and agents to identify jailbreaks, prompt injections, misuse cases, and bias exploitation.
• Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
• Apply structure by following taxonomies, benchmarks, and playbooks to maintain consistent testing.
• Document reproducibly to produce reports, datasets, and attack cases that customers can act on.
• Work independently and asynchronously to meet deadlines while improving AI model performance.

Qualifications

• Must-Have:
• Fluent Language Skills: Required: English & Urdu. Native fluency in English and Urdu is required.
• Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
• Strong communication skills to explain risks clearly to technical and non-technical stakeholders.
• Ability to thrive on moving across projects and customers.
• Preferred Experience:
• In Adversarial ML: jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction.
• In Cybersecurity: penetration testing, exploit development, reverse engineering.
• In socio-technical risk: harassment/disinfo probing, abuse analysis, conversational AI testing.
• In Creative probing skills: psychology, acting, writing for unconventional adversarial thinking.