Remote AI Red Team Specialist – Lead Researcher in Agentic Security

Posted 2 months ago

Description:

Join an advanced product and research team focused on building tools for dynamic testing of large language models (LLMs).
Collaborate with reverse engineers, pentesters, and data scientists to enhance agentic security.

Requirements:

Minimum of five years in enterprise red teaming or offensive research.
Proven experience in web application pentesting with a focus on remediation.
Familiarity with Mitre and OWASP frameworks; relevant security certifications are a plus.
Experience with agent-specific attack types and understanding of LLM pipelines.

Skills

Benefits