AI Safety Experts – 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 techniques such as jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation.

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

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

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

• Evaluate AI outputs related to sensitive subjects like bias, misinformation, and harmful behaviors.

• Identify vulnerabilities that automated testing may overlook.

• Enhance evaluation coverage and minimize unexpected issues in production.

• Fortify customer AI systems through adversarial testing.

⛳️ Requirements

• Native fluency in both English and Marathi is essential.

• Strong discernment regarding language and content is required.

• Capability to assess the accuracy, completeness, and appropriateness of AI responses and articulate the reasoning behind evaluations.

• Meticulous attention to detail, ensuring subtle errors, inconsistencies, and gaps are identified.

• Consistent adherence to guidelines and quality standards is necessary.

• Ability to convey reasoning clearly to both technical and non-technical audiences.

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

• Must hold independent contractor status.

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

• Preferred: experience in adversarial ML, including knowledge of jailbreak datasets, prompt injection, RLHF/DPO attacks, or model extraction.

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

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

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

🏝️ Benefits

• Fully remote position.

• Flexible work schedule; complete tasks at your convenience.

• Weekly payments through Stripe or Wise.

• Project durations may vary based on needs and performance.

• Optional participation in higher-sensitivity projects.

• Clear guidelines and wellness resources available for sensitive-content tasks.

• Reasonable accommodations provided upon request.

• Competitive compensation.

• Opportunity to collaborate with leading researchers.

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