AI / Emerging Tech Security Analyst

What You'll Do

• Analyze AI and LLM security scenarios to understand how models behave under adversarial, unexpected, or edge-case conditions
• Review and evaluate prompt injection attempts, data leakage vectors, model abuse cases, and system misuse scenarios
• Classify security vulnerabilities and recommend appropriate mitigations based on real-world impact and likelihood
• Assess AI system behavior against established security best practices and help identify gaps
• Work with realistic, scenario-based tasks that reflect the actual threat landscape facing deployed AI systems
• Complete task-based assignments independently on your own schedule

Who You Are

• Background in cybersecurity, information security, or a related technical field
• Familiar with threat modeling, vulnerability assessment, or security research — and genuinely curious about how AI systems are built and deployed
• Strong analytical thinker who can evaluate complex systems methodically and precisely
• Comfortable working with ambiguity and forming well-reasoned judgments on novel security scenarios
• Detail-oriented and consistent — you document your findings clearly and back them up with logic

Nice to Have

• Hands-on experience with penetration testing, red teaming, or adversarial research
• Familiarity with large language models (LLMs), generative AI tools, or AI/ML systems
• Knowledge of OWASP, MITRE ATT&CK, or other established security frameworks
• Background in applied security research, bug bounty programs, or secure software development
• Experience evaluating AI-generated outputs or working with AI safety concepts