AI Safety Expert – English, Odia

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

📋 Description

• Conduct red-team evaluations of conversational AI models and agents utilizing jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulation techniques.

• Create human data by annotating errors, categorizing vulnerabilities, and identifying systemic risks.

• Implement taxonomies, benchmarks, and playbooks to ensure consistent testing practices.

• Generate reproducible reports, datasets, and attack cases for customers to utilize.

• Assess AI outputs related to sensitive subjects such as bias, misinformation, and harmful behaviors.

• Identify vulnerabilities that automated testing fails to detect.

• Increase evaluation coverage and minimize unexpected outcomes in production.

• Fortify customer AI systems and promote the development of safer, more reliable AI technologies.

• Collaborate with top researchers on initiatives aimed at training and improving cutting-edge AI systems.

⛳️ Requirements

• Native proficiency in both English and Odia is essential.

• Strong judgment regarding language and content; ability to evaluate whether AI responses are accurate, complete, and suitable, and articulate the reasoning behind assessments.

• Keen attention to detail to identify subtle mistakes, inconsistencies, and gaps.

• Consistent adherence to guidelines and quality standards.

• Capability to communicate reasoning effectively to both technical and non-technical audiences.

• Flexibility to adapt across various projects, task types, and clientele.

• Candidates must not require H1-B or STEM OPT sponsorship.

• Status as an independent contractor is required.

• Preferred: experience in adversarial machine learning, encompassing jailbreak datasets, prompt injection, RLHF/DPO attacks, and model extraction.

• Preferred: background in cybersecurity, including penetration testing, exploit development, and reverse engineering.

• Preferred: experience in socio-technical risks, such as harassment/disinformation probing, abuse analysis, and conversational AI testing.

• Preferred: background in psychology, acting, or writing for innovative adversarial thinking.

🏝️ Benefits

• Fully remote position that allows you to work on your own schedule.

• Optional involvement in higher-sensitivity projects.

• Access to clear guidelines and wellness resources for projects involving sensitive content.

• Weekly payments processed via Stripe or Wise based on services rendered.

• Competitive compensation.

• Reasonable accommodations available upon request.

• Referral bonuses of up to $90 for each successful referral, subject to certain limits.

• Opportunity to work alongside leading researchers.

• Chance to gain experience in human data-driven AI red teaming.

• Engagement as an independent contractor.