AI Security Researcher — Red Team & Threat Modeling

COL Limited; London; On-site; NOK 1,827,000 - 2,385,000; Full time

Benefits offered by this job

Flexible working hours

Unlimited vacation

Relocation support and visa fees

Comprehensive health, dental andVision

Professional development budget

Job summary

Apollo Research is hiring AI Security Researchers to join the Infra & Security Team in London or San Francisco. You will identify, research and remediate threats from AI agents and redesign insider-risk concepts for a new class of risk.

You will red-team internal systems, design novel controls, track attacker tactics and ensure findings reach production with durable mitigations. This is a hands-on security engineering role in a fast-paced startup environment.

Qualifications

• 5+ years in security roles in a hands-on technical capacity.
• Direct experience with offensive security, threat modelling, red teaming.
• Engineering mindset: translate findings into fixes and automate.
• Startup pace: comfortable with ambiguity and changing priorities.
• Strong written communication producing threat models and reports.

Responsibilities

• Hold responsibility for the security of Apollo’s internal surfaces. Red-team internal software, infrastructure, and AI agent access controls.
• Design solutions for novel or emerging threats in the AI security space, where no existing playbook applies.
• Track adversary tactics, techniques, and campaigns relevant to Apollo's threat landscape, and translate that intelligence into detections.
• Own each finding through to a deployed fix. Build and roll out durable controls: checks, tests, defaults, detections.

Skills

5+ years security

Offensive security

Engineering mindset

Startup pace

Strong written communication

Job description

Apollo Research is hiring AI Security Researchers to join the Infra & Security Team in London or San Francisco. You will identify, research and remediate threats from AI agents and redesign insider-risk concepts for a new class of risk.

You will red-team internal systems, design novel controls, track attacker tactics and ensure findings reach production with durable mitigations. This is a hands-on security engineering role in a fast-paced startup environment.