Skip to content
Search jobs inside your AI agent. Claude, ChatGPT, Claude Code, Codex, Gemini, Cursor and Grok
Connect

NeuroStrike AS

AI Security Researcher — Offensive Exploit & Verification

Posted Updated

Description

NeuroStrike AS in Oslo seeks an experienced offensive security expert to drive our AI safety engine. You will research attack techniques, translate them into verifiable exploit logic, and benchmark against real CVEs and targets to reduce false positives.

You will review high-severity findings and help customers understand impact and remediation, while coordinating responsible disclosure when novel vulnerabilities are found. Eligibility for security clearance is required for certain assignments.

Research attack techniques and encode them into the engine. Build verification oracles that prove exploitability rather than guesswork. Benchmark the engine against real CVEs and lab targets to improve recall and reduce false positives. Review high-severity findings and help customers understand impact and remediation. Coordinate responsible disclosure when the engine discovers novel vulnerabilities. Hands-on penetration testing, red teaming or bug bounty experience. Deep understanding of web and API vulnerabilities (OWASP Top 10 and beyond). Comfortable scripting your own tooling (Python, Go, TypeScript or similar). Strong written communication — you can explain a complex exploit chain clearly. High ethical standards and respect for scope and authorization. Willing and eligible for security clearance at NATO level for certain assignments.

Skills

Apply

See also

Security jobs by country — openings, pay and top skills →