Cybersecurity Experts for AI Training

About the role

Gramian Consultancy is seeking experienced cybersecurity professionals to design and implement realistic security‑focused coding challenges for advanced AI evaluation. The role is contract‑based, remote, and requires close collaboration with AI benchmarking teams.

Key responsibilities

• Design vulnerable multi‑component applications in Go, Python, Node.js or Rust.
• Develop deterministic exploit chains that combine multiple vulnerability categories.
• Build reproducible evaluation environments using Docker and automated validation tools.
• Create test cases and verification logic for vulnerability detection and remediation.
• Analyze AI‑generated outputs to spot gaps in security reasoning.
• Model real‑world vulnerability classes inspired by CVEs, bug bounty findings and production incidents.
• Ensure tasks remain scalable, reproducible and resistant to public dataset contamination.

Required profile

• Minimum 4 years of experience in cybersecurity, application security, vulnerability research or offensive security.
• Hands‑on experience with vulnerability discovery, exploit development, secure code review or patch validation.
• Strong understanding of web security concepts such as authentication, sessions, OAuth, JWT, SSRF, injection and access‑control flaws.
• Experience with cryptographic weaknesses, filesystem attacks or privilege‑escalation scenarios.

Required skills

• Go, Python, Node.js, Rust (at least two).
• Docker and container orchestration.
• SAST, fuzzers, IAST or similar security testing frameworks.
• Web security protocols (OAuth, JWT) and common attack vectors (SSRF, injection, XSS).
• Vulnerability research tools and CVE analysis.

What we offer

• Short‑term contract (minimum 4 weeks) with flexible remote work.
• Opportunity to influence cutting‑edge AI safety research.
• Collaboration with a multidisciplinary team of AI and security experts.