
AI Safety Expert, English β Thai
Posted Sep 15

Posted Sep 15
This is a fully remote position, open to applicants in United States.
β’ Conduct red-team evaluations of conversational AI models and agents through methods such as jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulations.
β’ Create human-generated data by annotating failures, categorizing vulnerabilities, and identifying systemic risks.
β’ Implement taxonomies, benchmarks, and playbooks to ensure consistent testing procedures.
β’ Generate reproducible reports, datasets, and attack scenarios.
β’ Assess AI outputs related to sensitive issues, including bias, misinformation, and harmful behaviors.
β’ Identify vulnerabilities that automated testing may overlook.
β’ Enhance evaluation coverage and minimize unexpected outcomes in production.
β’ Fortify customer AI systems, promoting safer and more reliable AI solutions.
β’ Native or fluent proficiency in both English and Thai.
β’ Previous experience in red teaming, especially in AI adversarial tasks, cybersecurity, or socio-technical probing.
β’ Capability to adversarially probe AI systems and challenge them to their limits.
β’ Proficiency in using frameworks or benchmarks for systematic testing.
β’ Skill in articulating risks clearly to both technical and non-technical audiences.
β’ Flexibility to adapt to various projects and client needs.
β’ Preferred expertise in adversarial machine learning, cybersecurity, socio-technical risk, or innovative probing methods.
β’ Engagement as an independent contractor.
β’ Must not require H1-B or STEM OPT sponsorship.
β’ Fully remote position.
β’ Flexible working hours, allowing completion of tasks on your own schedule.
β’ Weekly payments facilitated through Stripe or Wise.
β’ Project durations may be extended, shortened, or concluded early based on requirements and performance evaluations.
β’ Access to wellness resources and clear guidelines for projects involving higher sensitivity.
β’ Reasonable accommodations available upon request.
β’ Referral program that rewards up to $140 for every successful referral made.
The College Board
Mercor
Mercor
Get handpicked remote jobs straight to your inbox weekly.