AI Safety Experts — English & Odia

📋 Description

• Test jailbreaks, prompt injections, misuse scenarios, bias, and multi-turn manipulation
• Identify vulnerabilities, failure modes, and safety gaps in automated testing
• Annotate model failures, classify vulnerabilities, and document adversarial examples
• Apply taxonomies, benchmarks, and playbooks for consistent evaluations
• Create structured attack cases, datasets, and reports to improve AI safety
• Communicate risks to technical and non-technical stakeholders

🎯 Requirements

• Native-level fluency in English and Odia
• Experience with AI red teaming, adversarial AI, cybersecurity, or related fields
• Adversarial mindset with ability to identify manipulation opportunities
• Systematic testing using frameworks, benchmarks, and structured methodologies
• Strong written/verbal communication and documentation skills
• Independent work style, prioritization, and rapid adaptation

🎁 Benefits

• Fully remote work with flexible project timelines
• Independent contractor engagement with weekly payments via Stripe or Wise
• Competitive compensation based on expertise and assignment
• Opportunity to work on cutting-edge AI safety projects
• Direct contribution to safer, more trustworthy AI systems
• Exposure to emerging AI evaluation and red-teaming methods