AI Safety Expert, English, Marathi

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

📋 Description

• Conduct red-team assessments on conversational AI models and agents through methods such as jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulation.

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

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

• Generate reproducible reports, datasets, and attack scenarios for clients.

• Evaluate AI outputs related to sensitive issues like bias, misinformation, or harmful behaviors.

• Identify vulnerabilities that automated tests may overlook.

• Broaden evaluation coverage and minimize unexpected issues in production.

• Assist clients in enhancing the safety, robustness, and reliability of AI systems.

⛳️ Requirements

• Required fluent/native proficiency in English and Marathi.

• Strong judgment regarding language and content; capability to evaluate the accuracy, completeness, and appropriateness of AI responses while providing clear explanations.

• Meticulous attention to minor errors, inconsistencies, and omissions.

• Consistent adherence to guidelines and quality standards.

• Ability to articulate reasoning effectively to both technical and non-technical audiences.

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

• Must hold independent contractor status.

• Note: H1-B and STEM OPT candidates are not eligible.

• Preferred: Experience in adversarial machine learning, including jailbreak datasets, prompt injection, RLHF/DPO attacks, or model extraction.

• Preferred: Background in cybersecurity, covering penetration testing, exploit development, or reverse engineering.

• Preferred: Experience in socio-technical risk assessment, such as harassment/disinformation probing, abuse analysis, or conversational AI evaluation.

• Preferred: Background in psychology, acting, or writing to foster unconventional adversarial thinking.

🏝️ Benefits

• Fully remote position.

• Flexible working hours; manage your own schedule.

• Weekly payments via Stripe or Wise based on services provided.

• Project durations can be adjusted based on requirements and performance.

• Access to wellness resources and clear protocols for high-sensitivity projects.

• Reasonable accommodations available upon request.

• Referral program: earn up to $90 for each successful referral, with no cap on the number of referrals.

• Opportunity to collaborate with leading researchers.

• Gain experience in human data-driven AI red teaming at the forefront of safety.