Remote Cybersecurity Expert – AI Model Evaluation

About the role

Turing is seeking a Remote Cybersecurity Expert to design and develop advanced evaluation tasks for frontier AI models. You will create realistic, adversarial security scenarios that test an AI model’s ability to understand code, detect vulnerabilities, and reason about complex software security problems.

Key responsibilities

• Design multi‑vulnerability codebases in languages such as Go, Python, Node.js, or Rust.
• Build multi‑stage attack chains by combining different vulnerability classes into realistic exploit scenarios.
• Create deterministic evaluation frameworks using containerized environments and automated verification systems.
• Write security test cases and exploit checks to ensure vulnerabilities are detected and mitigated.
• Analyze AI model outputs and reasoning traces to identify failure points in security understanding.
• Craft adversarial scenarios including misleading documentation, obfuscated code, and edge‑case logic.
• Balance real‑world CVE‑based scenarios with synthetic vulnerability classes for robust evaluation.
• Ensure evaluation tasks are reproducible, scalable, and resistant to data contamination.

Required profile

• 4+ years of experience in cybersecurity, application security, or vulnerability research.
• Hands‑on experience with vulnerability discovery (CVE exposure, bug bounty, red teaming, or CTFs) and secure code review.
• Deep understanding of web security, injection attacks, cryptographic flaws, and filesystem vulnerabilities.
• Experience building or using security tools such as SAST, fuzzing, or IAST.

Required skills

• Proficiency in at least one language: Go, Python, Node.js, or Rust.
• Docker and containerized environments.
• Linux internals and system‑level behavior.
• Automated testing frameworks (e.g., pytest).
• Security tooling experience: SAST, fuzzing, IAST.