Cybersecurity Expert

About Turing

Turing is a San Francisco-based research accelerator supporting frontier AI labs and enterprises deploying advanced AI systems.

The company works across:

• AI research acceleration
• High-quality training pipelines
• AI coding and reasoning systems
• Enterprise AI transformation initiatives

Turing collaborates with leading AI labs on projects involving coding, reasoning, STEM, multilinguality, multimodality, and AI agents.

Job Summary

Turing is seeking experienced Cybersecurity Experts to design and develop advanced evaluation tasks for frontier AI models.

This role operates at the intersection of:

• Offensive security
• Defensive engineering
• AI evaluation
• Vulnerability research

Contributors will build realistic adversarial security scenarios that evaluate AI systems on:

• Code understanding
• Vulnerability detection
• Security reasoning
• Exploit analysis

This is not a traditional security operations role. The focus is on creating reproducible AI evaluation environments and deterministic security benchmarks grounded in real-world vulnerability classes.

What You'll Work On

• Design and develop multi-vulnerability codebases across languages such as:

  • Go
  • Python
  • Node.js
  • Rust

• Create realistic multi-stage attack chains combining multiple vulnerability classes

• Build deterministic evaluation environments using:

  • Docker
  • Containerized systems
  • Automated verification frameworks

• Write:

  • Security test cases
  • Exploit validation checks
  • Vulnerability detection benchmarks

• Analyze AI model outputs and reasoning traces to identify failures in security understanding

• Create adversarial evaluation scenarios involving:

  • Misleading documentation
  • Obfuscated code
  • Edge-case logic

• Balance:

  • Real-world CVE-based vulnerabilities
  • Synthetic vulnerability scenarios

to improve AI evaluation robustness.

• Ensure evaluation tasks are:
  • Reproducible
  • Scalable
  • Resistant to data contamination

Required Skills & Qualifications

• Minimum 4 years of experience in:

  • Cybersecurity
  • Application security
  • Vulnerability research

• Hands-on experience with:

  • Vulnerability discovery
  • CVEs
  • Bug bounty workflows
  • Red teaming
  • CTF environments

• Strong understanding of:

  • Secure code review
  • Production patching
  • Web application security
  • OAuth and JWT vulnerabilities
  • Access control issues
  • Injection attacks
  • SSRF vulnerabilities
  • Cryptographic attack patterns
  • Filesystem vulnerabilities

• Experience building or using:

  • SAST tools
  • Fuzzing systems
  • IAST frameworks

• Proficiency in one or more languages:

  • Go
  • Python
  • Node.js
  • Rust

• Familiarity with:

  • Docker
  • Linux internals
  • Automated testing frameworks
  • Obfuscated code analysis

• Strong analytical and attack-chain reasoning abilities

Perks

• Fully remote work environment
• Opportunity to contribute to cutting-edge AI projects with leading LLM organizations

Contract Details

• Contractor engagement

• Duration:

  • Approximately 1 month

• Expected start:

  • Next week

• Required commitment:

  • 40 hours per week
  • Minimum 4-hour overlap with PST timezone

• No medical or paid leave included

Evaluation Process

Round 1

Technical Interview (60 minutes)

Round 2

Delivery Interview (30–45 minutes)