AI Safety Expert, English, Bengali

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

📋 Description

• Test and challenge conversational AI models and agents using jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulation techniques.

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

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

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

• Identify vulnerabilities that automated tests may overlook.

• Broaden evaluation coverage and minimize unexpected issues in production.

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

• Work alongside prominent AI researchers on initiatives aimed at training and improving cutting-edge AI systems.

⛳️ Requirements

• Proficient language capabilities in both English and Bengali.

• Native proficiency in English and Bengali is essential.

• Previous experience in red teaming within the realms of AI adversarial operations, cybersecurity, or socio-technical investigations.

• Capacity to challenge AI systems adversarially and drive them to their limits.

• Familiarity with frameworks or benchmarks for systematic testing.

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

• Flexibility to adapt across various projects and clients.

• Experience in adversarial machine learning, 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).

• Knowledge of socio-technical risks, including harassment/disinformation investigations, abuse analysis, or conversational AI assessment (preferred).

• Innovative probing experience in psychology, acting, or writing (preferred).

• Candidates must not hold H1-B or STEM OPT status.

🏝️ Benefits

• Fully remote position.

• Flexible working hours, allowing you to manage your own schedule.

• Weekly payments through Stripe or Wise.

• Project durations may vary based on needs and performance, with options for extension, shortening, or early conclusion.

• Participation in higher-sensitivity projects is voluntary.

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

• Competitive salary.

• Collaborate with top-tier researchers in the field.

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