AI Red Team Researcher
Core
Research emerging agentic technologies to uncover new exploits, attack vectors, and risks in the AI ecosystem, from initial exploitation to impact.
Role type
Junior offensive security researcher (AI/LLM)
Builds
Tooling, harnesses, and test frameworks to scale attack discovery and contribute to internal red team infrastructure.
Domain
AI security, Agentic AI, LLMs, and surrounding ecosystem (plugins, connectors, MCP servers, orchestration frameworks)
Deliverable
production ML models
Required skills
Red teaming, vulnerability research, Python, JavaScript, bash, cloud security, application security, AI vulnerability analysis (prompt injections, jailbreaks, reconnaissance)
Preferred skills
None stated
Technologies
Python, JavaScript, bash
Responsibilities
Research emerging agentic technologies and uncover new exploits, attack vectors and risks; Build tooling, harnesses, and test frameworks to scale attack discovery; Investigate the surrounding ecosystem including plugins, connectors, MCP servers, and orchestration frameworks; Work with product and engineering to translate offensive findings into new defense capabilities.
Seniority
Junior, hands-on IC (via careerplan.io/jobs/19-000-C5-07D-ai-red-team-researcher-at-zenity)
