The role
Job description
Job description
Help develop realistic security challenges that evaluate how advanced AI coding models identify and fix software vulnerabilities. This remote freelance project combines vulnerability research, reproducible testing and technical review across open-source software.
What you'll do
- Investigate vulnerabilities from CVEs, security advisories, bug reports and open-source repositories.
- Reproduce security issues and build tests that demonstrate the vulnerability and validate a secure fix.
- Create audit-and-patch tasks with reproducible Docker environments and clear instructions.
- Develop robust verifiers that resist hardcoded solutions and test manipulation.
- Review AI-generated patches and reasoning, and document technical findings.
What we're looking for
- 5+ years of professional software engineering experience.
- Expert proficiency in at least one of Python, JavaScript/TypeScript, Java, C/C++, C#, Go, Rust, Ruby, PHP, Kotlin or Swift.
- Strong knowledge of CWE, CVE and the OWASP Top 10, with experience reproducing vulnerabilities and writing security tests.
- Hands-on experience with sanitizers, fuzzers and static analysis tools such as CodeQL or Semgrep.
- Strong working knowledge of Git, Linux, Bash and Docker.
- Clear technical writing and the ability to work independently.
Project details
The expected engagement is three months, with availability for 40 hours per week, including four hours of overlap with Pacific Time. The team is looking for someone who can start soon. Selection includes a technical interview lasting approximately one hour.
Compensation
$15 USD/hour.