AI Safety Expert, English – Odia

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

📋 Description

• Conduct red team activities on conversational AI models and agents

• Investigate models for vulnerabilities such as jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulation

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

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

• Generate reproducible reports, datasets, and attack cases for client use

• Assess AI outputs related to sensitive topics like bias, misinformation, and harmful behaviors

• Enhance evaluation coverage and reveal vulnerabilities that automated tests may overlook

• Develop artifacts that enhance the robustness of customer AI systems

⛳️ Requirements

• Required fluent/native proficiency in both English and Odia

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

• Capability to probe AI models through techniques such as jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation

• Skills in annotating failures, classifying vulnerabilities, and identifying systemic risks

• Ability to adhere to taxonomies, benchmarks, and playbooks

• Proficiency in producing reproducible reports, datasets, and attack scenarios

• Capability to articulate risks clearly to both technical and non-technical stakeholders

• Flexibility across various projects and client needs

• Preferred specialties include adversarial machine learning, cybersecurity, socio-technical risk, and innovative probing

• Engagement as an independent contractor

• H1-B and STEM OPT candidates are not eligible

🏝️ Benefits

• Fully remote position

• Flexible working hours; complete tasks on your own schedule

• Receive weekly payments through Stripe or Wise

• Chance to gain experience in human data-driven AI red teaming at the forefront of safety

• Direct contribution to enhancing the robustness, safety, and trustworthiness of AI systems

• Collaborate with leading researchers in the field

• Competitive compensation

• Participation in higher-sensitivity projects is optional

• Clear guidelines and wellness resources available for higher-sensitivity projects

• Reasonable accommodations provided upon request

• Referral bonuses of up to $90 for each successful referral, with no limit on the number of referrals