AI Safety Expert – English, Assamese

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

📋 Description

• Engage in red-team evaluations of conversational AI models and agents.

• Conduct tests for jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulations.

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

• Utilize taxonomies, benchmarks, and playbooks to maintain consistency in testing.

• Prepare reproducible reports, datasets, and attack cases for clients.

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

• Broaden evaluation coverage and minimize unexpected issues during production.

• Participate in projects aimed at training and refining AI systems.

⛳️ Requirements

• Must possess native fluency in both English and Assamese.

• Previous experience in red teaming focused on AI adversarial tasks, cybersecurity, or socio-technical probing.

• Proficiency in probing AI models through jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation.

• Capability to annotate failures, categorize vulnerabilities, and pinpoint systemic risks.

• Familiarity with following taxonomies, benchmarks, and playbooks.

• Competence in generating reproducible reports, datasets, and attack cases.

• A curious and adversarial mindset toward system testing.

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

• Flexibility to adapt across various projects and clients.

• Status as an independent contractor is required.

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

🏝️ Benefits

• Fully remote position.

• Flexible work schedule allowing you to choose your own hours.

• Weekly compensation via Stripe or Wise.

• Optional participation in high-sensitivity projects.

• Clear guidelines and wellness resources available for projects involving sensitive content.

• 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 package.

• Collaboration with leading researchers in the field.

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