Senior Software Security Engineer - AI Benchmark Development
Gramian Consulting Group (company site, opens in a new tab)5+ yrsRemoteDirect career pageEst. 14–26 LPA
Posted 4d ago
Reach people at Gramian Consulting Group
People at this company you can reach
Log in to see who works here
Create a free account or log in to see the people at Gramian Consulting Group you could write to:
- Recruiters & HR
- People in this function
- Work addresses
Your match
Against your primary resume
Log in to see your match score
Create a free account or log in to unlock your CV match score across:
- Role fit
- Experience
- Industry relevance
Protocol Intelligence
How competitive this role is
Competition
Background fit
Strictness
Log in to see why each signal reads the way it does.
Job description
Structured overview of role & requirements
About This Role
- Turn real-world vulnerabilities from CVEs, advisories, and bug reports into Harbor-format audit-and-patch benchmarks across multiple languages.
- Reproduce vulnerabilities, build Docker-based test environments and robust verifiers, then assess AI-generated patches for correct fixes rather than superficial pattern matching.
- Contractor assignment: 3 months, 40 hours/week, fully remote; expected start next week.
Minimum Requirements
- Work Experience Required: 5+ years of professional software engineering experience.
- Expert proficiency in at least one listed language: Python, JavaScript/TypeScript, Java, C/C++, C#, Go, Rust, Ruby, PHP, Kotlin, or Swift.
- Practical knowledge of CWE, CVE, OWASP Top 10, and common vulnerability classes; ability to reproduce vulnerabilities and create proof-of-vulnerability tests.
- Experience with sanitizers, fuzzers, or static-analysis tools such as CodeQL or Semgrep; strong Git, Linux, Bash, and Docker skills, plus ability to build automated tests and reproducible environments.
Ideal Candidate Profile
- Has practical application-security experience investigating vulnerabilities in real software and translating findings into reliable reproductions and fixes.
- Can build evaluation tasks and verifiers that test understanding of vulnerability causes, not recall of known patches or recognizable patterns.
- Fits an independent, research-oriented workflow involving technical documentation and structured review of security patches.