Senior AI Security Researcher
Own our threat intelligence pipeline. You'll design and run red team exercises against AI systems — LLMs, agent frameworks, RAG pipelines — and translate your findings into detection logic and customer-facing reports.
- 5+ years in offensive security, red teaming, or application security research
- Hands-on experience with LLM prompt injection, jailbreaks, or model extraction attacks
- Familiarity with OWASP LLM Top 10 and agentic AI threat models
- Strong Python; comfortable reading model configs, inference code, and API traces
- Prior work publishing CVEs, research papers, or conference talks is a strong plus