AI Safety Expert – English, Bengali

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

📋 Description

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

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

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

• Deliver reproducible reports, datasets, and case studies for clients.

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

• Identify vulnerabilities that automated testing may overlook.

• Enhance evaluation coverage to minimize production surprises.

• Fortify customer AI systems, contributing to the development of safer, more resilient, and trustworthy AI technologies.

⛳️ Requirements

• Proficient/native fluency in English and Bengali is mandatory.

• Strong judgment regarding language and content; capability to evaluate whether AI responses are accurate, comprehensive, and suitable.

• Skill in recognizing subtle errors, inconsistencies, and gaps.

• Ability to consistently adhere to guidelines and quality standards.

• Competence in clearly articulating reasoning to both technical and non-technical audiences.

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

• Engagement as an independent contractor is required.

• Candidates should not be on an H1-B visa or STEM OPT program.

• Preferred qualifications include specialties in adversarial ML, 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 innovative adversarial writing.

🏝️ Benefits

• Fully remote position.

• Flexible work schedule; complete tasks at your convenience.

• Weekly payments through Stripe or Wise based on services rendered.

• Project duration may be extended, shortened, or concluded early based on needs and performance.

• Reasonable accommodations available upon request.

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

• Collaborate with top researchers in the field.

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