AI Safety Expert – English, Odia

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

📋 Description

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

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

• Adhere to established taxonomies, benchmarks, and playbooks to ensure consistency in testing.

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

• Investigate AI systems for vulnerabilities that automated testing may overlook.

• Broaden evaluation coverage across various scenarios.

• Enhance customer AI systems and contribute to the development of safer, more reliable AI.

⛳️ Requirements

• Native proficiency in both English and Odia is essential.

• Previous experience in red-teaming related to AI adversarial activities, cybersecurity, or socio-technical investigations.

• Capability to probe systems in an adversarial manner and test their limits.

• Familiarity with frameworks or benchmarks for structured testing processes.

• Ability to clearly communicate risks to both technical and non-technical audiences.

• Flexibility to adapt across various projects and clients.

• Candidates must be independent contractors.

• H1-B and STEM OPT candidates will not be considered.

🏝️ Benefits

• Fully remote position.

• Flexible scheduling to suit your needs.

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

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

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

• Direct involvement in enhancing the robustness, safety, and trustworthiness of AI systems.

• Competitive compensation.

• Collaboration with prominent researchers in the field.

• Reasonable accommodations available upon request.

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