Red Team Specialist - Cyber

Remote San Francisco FullTime

Posted 27d ago

Job Location

San Francisco

Tech Stack

Remote Work Policy

Fully remote

Employment Type

FullTime

Categories

Applied AI Engineer

About the job

As a Red Team Specialist focused on cyber, you will help answer practical questions about the cyber capabilities our models can provide to real-world attackers and the effectiveness of our safeguards against sophisticated techniques. This role blends scaled evaluation with expert-driven testing, requiring a strong foundation in either cybersecurity or model evaluations, with fluency in the other. You will primarily focus on model cyber capabilities and safeguards, with a portion of your time dedicated to testing novel abuse risks in agentic systems. This role is located in San Francisco, CA or Seattle, WA, utilizing a hybrid work model.

Responsibilities

  • Design and run rigorous evaluations of model cyber capabilities and safeguards, including policy adherence, correct refusal, over refusal, and resilience to jailbreaking and other adversarial techniques.
  • Conduct hands-on testing to understand what models can enable when used by experienced security practitioners.
  • Distinguish benchmark or policy failures from behavior that creates meaningful real-world risk.
  • Build and improve automated testing infrastructure for repeatable measurement, rapid iteration, and statistically grounded analysis.
  • Test novel abuse risks in agentic systems, including indirect prompt injection and agent hijacking.
  • Translate findings into clear risk assessments and actionable recommendations for partner teams.
  • Contribute to Safety Bug Bounty work, particularly where reports require cyber expertise.

Requirements

  • Substantial depth in cybersecurity (e.g., application security, penetration testing, vulnerability research, adversary simulation, red-team operations) OR AI model evaluation (e.g., designing evals, building agentic harnesses, automating adversarial testing, constructing datasets, analyzing model behavior at scale).
  • Working literacy across both cybersecurity and model evaluation, with an interest in developing further depth.
  • Ability to write code and build practical testing tools for automation, orchestration, or analysis.
  • An attacker mindset and interest in discovering failure modes.
  • Clear written and verbal communication skills, including explaining technical findings to diverse audiences.
  • Experience working across technical and non-technical teams to drive decisions and mitigations.

Benefits

  • Hybrid work model (3 days in office per week)
  • Relocation assistance

About OpenAI

Get new AI jobs in your inbox

A weekly digest of the newest AI engineering roles.

© 2026 AI Job Board. All rights reserved.