Senior Software Security Engineer - AI Benchmark Development

New
G
Gramian ConsultancySoftware security
Workable locations: Brazil. Bangladesh. Colombia. Egypt. Ghana. IndiaContractSenior
Salary not disclosed
Apply NowOpens the employer's application page

Job Details

Experience
5+ years of professional software engineering experience.
Required Skills
DockerPythonBashGitLinux

Requirements

  • Have 5+ years of professional software engineering experience.
  • Have expert-level proficiency in at least one of Python, JavaScript/TypeScript, Java, C/C++, C#, Go, Rust, Ruby, PHP, Kotlin, or Swift.
  • Demonstrate a strong understanding of software security principles and common vulnerability classes.
  • Have practical knowledge of CWE, CVE, and the OWASP Top 10.
  • Be able to independently reproduce vulnerabilities and develop proof-of-vulnerability tests.
  • Have hands-on experience with sanitizers, fuzzers, and static-analysis tools such as CodeQL or Semgrep.
  • Have strong proficiency with Git, Linux, Bash, and Docker.
  • Be able to create automated tests and reproducible technical evaluation environments.
  • Have strong technical writing skills to explain security issues and remediation requirements.
  • Be able to work independently in a fully remote, research-oriented environment.

Responsibilities

  • Source and investigate vulnerabilities from CVEs, security advisories, bug reports, and open-source repositories.
  • Classify vulnerabilities using applicable CWE identifiers and map them to OWASP Top 10 categories where appropriate.
  • Reproduce security issues and develop proof-of-vulnerability tests.
  • Build Harbor-format audit-and-patch tasks across programming languages and software ecosystems.
  • Write task instructions that describe security issues without revealing vulnerable code, exploit details, or expected remediation.
  • Create reproducible Docker-based environments with pinned dependencies and setup and execution instructions.
  • Design and harden automated verifiers against gaming, test manipulation, hardcoded solutions, and overfitting.
  • Review and score AI-generated patches and technical reasoning using structured security and engineering rubrics.
  • Identify tasks solvable through superficial pattern matching or copying known upstream patches.
  • Document vulnerability context, reproduction steps, expected behavior, patch requirements, test methodology, and review decisions.
View Full Description & ApplyYou'll be redirected to the employer's site
View details
Apply Now