AI Safety Expert – English, Assamese

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

📋 Description

• Conduct red team assessments on conversational AI models and agents by utilizing jailbreak techniques, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulations.

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

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

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

• Examine AI outputs related to sensitive subjects including bias, misinformation, and detrimental behaviors.

• Identify vulnerabilities that automated testing may overlook.

• Broaden evaluation scope and minimize unexpected issues in production.

• Enhance customer AI systems to make them more robust, secure, and reliable.

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

⛳️ Requirements

• Proficiency in both English and Assamese is essential.

• Previous experience in red teaming within AI adversarial contexts, cybersecurity, or socio-technical analysis.

• Capability to probe systems adversarially and challenge them to their limits.

• Familiarity with structured frameworks, taxonomies, benchmarks, or playbooks.

• Ability to effectively communicate risks to both technical and non-technical stakeholders.

• Flexibility to adapt across various projects and client needs.

• Expertise or interest in areas such as jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction, penetration testing, exploit development, reverse engineering, harassment/disinformation probing, abuse analysis, conversational AI testing, psychology, acting, or writing.

• Must operate as an independent contractor.

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

🏝️ Benefits

• Work remotely from anywhere.

• Enjoy a flexible work schedule and the freedom to manage your own time.

• Receive weekly payments through Stripe or Wise.

• Competitive compensation.

• Collaborate with leading researchers in the field.

• Gain experience in human data-driven AI red teaming.

• Access to wellness resources and clear guidelines for projects requiring higher sensitivity.

• Participation in higher-sensitivity projects is optional.

• Reasonable accommodations available upon request.

• Earn referral payments of up to $90 for each successful referral.