AI Safety Expert, English, Thai

This is a fully remote position, open to applicants in United States.

📋 Description

• Engage in red teaming for conversational AI models and agents

• Test for jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulations

• Create high-quality human data through annotating failures, classifying vulnerabilities, and identifying systemic risks

• Utilize taxonomies, benchmarks, and playbooks to maintain consistency in testing

• Generate reproducible reports, datasets, and attack cases for clients

• Identify vulnerabilities that automated testing may overlook

• Broaden evaluation coverage and minimize unexpected production issues

• Analyze AI outputs related to sensitive subjects such as bias, misinformation, or harmful behaviors

• Collaborate with leading researchers and assist in the training and enhancement of cutting-edge AI systems

⛳️ Requirements

• Proficient/native fluency in both English and Thai

• Previous experience in red teaming, specifically in AI adversarial work, cybersecurity, or socio-technical exploration

• Capability to challenge AI systems using adversarial inputs

• Familiarity with jailbreaks, prompt injections, misuse scenarios, bias exploitation, or multi-turn manipulations

• Skill in annotating failures, classifying vulnerabilities, and identifying systemic risks

• Competence in adhering to taxonomies, benchmarks, and playbooks

• Ability to produce reproducible reports, datasets, and attack cases

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

• Flexibility to adapt across various projects and clients

• Preferred specialties include adversarial ML, cybersecurity, socio-technical risks, or creative probing

• Must be capable of working as an independent contractor

• H1-B and STEM OPT candidates are not eligible

🏝️ Benefits

• Fully remote position

• Flexible working hours / ability to set your own schedule

• Weekly compensation through Stripe or Wise

• Project durations may be adjusted based on needs and performance outcomes

• Access to wellness resources and clear protocols for sensitive projects

• Direct involvement in human data-driven AI red teaming

• Chance to contribute to the development of safer, more robust, and trustworthy AI systems

• Competitive compensation

• Referral bonus of up to $140 for each successful referral