Senior Security Researcher
Core
Research and exploit weaknesses in LLM applications and autonomous agents to improve AI security and offensive security product offerings.
Role type
Senior Security Researcher (AI/LLM focus)
Builds
Attack tooling, agent harnesses, reproducible evaluations, and offensive security products
Domain
Artificial Intelligence, Large Language Models (LLM), Offensive Security
Deliverable
production ML models
Required skills
AI red teaming, offensive security, LLM fundamentals, harness engineering, agent security, evals and benchmarks, experimental design, research engineering, failure analysis, exploit validation
Preferred skills
Collaborative research, technical and non-technical communication
Technologies
Python, APIs, containers, browser automation
Responsibilities
Conduct AI red teaming (prompt injection, jailbreaks, data leakage), perform web/API penetration testing and business logic attacks, build agent orchestration tools, design realistic attack scenarios and benchmarks, analyze model and environment failures, produce reproducible proofs of concept and remediation reports.
Seniority
Senior, hands-on IC
