Cybersecurity Expert

Cybersecurity Expert

Engagement: Short-term contract. The listing gives both a 3-month engagement and a 1-month contract duration; please confirm the correct term. Positions: 4 Start: Immediate / expected next week Availability: 40 hours per week, with 4 hours of overlap with PST Rate: Maximum $20 per hour Interview: Technical delivery interview

Role overview

Design and develop advanced evaluation tasks for frontier AI models. Build realistic, adversarial security scenarios that assess an AI model’s ability to understand code, detect vulnerabilities, and reason through complex software security problems. The role combines offensive security, defensive engineering, and AI evaluation, using reproducible environments and deterministic benchmarks grounded in real-world vulnerability classes.

Responsibilities

• Develop multi-vulnerability (multi-CWE) codebases in Go, Python, Node.js, or Rust.
• Create realistic, multi-stage attack chains that combine vulnerability classes.
• Build deterministic evaluation frameworks with containerized environments and automated verification.
• Write security test cases and exploit checks to verify vulnerability detection and mitigation.
• Analyze AI model outputs and reasoning traces to identify security-understanding failure points.
• Craft adversarial scenarios, including misleading documentation, obfuscated code, and edge-case logic.
• Balance CVE-based scenarios with synthetic vulnerability classes.
• Ensure evaluation tasks are reproducible, scalable, and resistant to data contamination.

Requirements

• 4+ years of experience in cybersecurity, application security, or vulnerability research.
• Hands-on vulnerability discovery experience, such as CVEs, bug bounty, red teaming, or CTFs.
• Secure code review and production-grade patching experience.
• Strong knowledge of web security, including authentication, sessions, OAuth, and JWT vulnerabilities; SSRF; injection attacks; access control; cryptographic vulnerabilities; and filesystem vulnerabilities.
• Experience with security tools such as SAST, fuzzing, or IAST.
• Proficiency in at least one of Go, Python, Node.js, or Rust.
• Familiarity with Docker, Linux internals, and system-level behavior.
• Penetration-testing experience and ability to write automated tests.
• Ability to analyze obfuscated or minified code and reason through attack chains.
• Strong analytical and problem-solving skills.

Work arrangement and terms

Fully remote contractor assignment. The listing describes the role as a short-term contract and notes no medical or paid leave.