Skip to content
← OpenAI

Red Team Specialist - Cyber

OpenAI · San Francisco · Seattle · Washington, DC

CHECKED 1H AGO

Frontier labremote$198k–$320k
Apply on the lab’s site ↗

At a glance

Highlights

  • Evaluate model cyber capabilities and safeguard resilience under adversarial attack.
  • Probe agentic abuse risks like prompt injection and agent hijacking.
  • Translate red-team findings into actionable risk assessments for partners.

What they offer

  • Equity
  • Relocation assistance

Ideal candidate

Security practitioner or eval builder with attacker mindset who judges real-world cyber risk and turns ambiguous threats into rigorous, automated tests.

Requirements

  • Deep experience in cybersecurity such as application security, penetration testing, vulnerability research, adversary simulation, or red-team operations, or in AI model evaluation such as evals, agentic harnesses, and adversarial testing
  • Working literacy across both cybersecurity and model evaluation
  • Ability to write code and build practical testing tools for automating experiments and analyzing results
  • Attacker mindset with interest in discovering failure modes standard evaluations may miss
  • Clear written and verbal communication and experience working across technical and non-technical teams
remote policy
Hybrid, 3 days in office per week

Lab profile

About OpenAI

Builds safe frontier AI models and products like ChatGPT for broad benefit.

What they build

  • ChatGPT
  • OpenAI API
  • Frontier AI models

Known for

  • Frontier-scale distributed ML training
  • Massive GPU fleet and data center operations
  • Exabyte-scale data lakes and streaming
  • AI alignment and safety research

Key facts

  • Operates one of the world's largest GPU fleets
More about OpenAI →
Apply on the lab’s site ↗