Strix
Security Researcher
New York +1 · On-site · Full-time · Posted Aug 24, 2026
- Location
- New York
San Francisco - Experience
- 3+ years of hands-on offensive security experience.
About the job
Find and validate real-world vulnerabilities, then translate offensive-security expertise into capabilities, benchmarks, and detection strategies for Strix’s AI penetration-testing agents.
What you'll do
- Discover and exploit vulnerabilities in web applications, APIs, cloud infrastructure, and open-source software.
- Encode offensive-security techniques into agent behaviors, tools, and playbooks; build vulnerable environments and benchmarks.
- Analyze agent findings, distinguish valid issues from noise, and reduce false positives.
What they ask for
- 3+ years of hands-on offensive security experience, such as penetration testing, red teaming, bug bounty, or vulnerability research.
- Deep understanding of web application security, exploitation techniques, and modern attack surfaces.
- Programming experience in Python or similar, with comfort building tools.
Nice to have
- CVEs, published research, CTF results, or a strong bug bounty track record.
Tools
Python
AI focus
Develop and evaluate autonomous AI penetration-testing agents by encoding offensive-security techniques, building benchmarks, and validating findings.
Model-written summary · the original posting is authoritative