CareerPlan

AI Security Researcher

London & San FranciscoFull-time£214k–£280k2026-08-28 → 2026-11-19
Hybrid · United Kingdom, United StatesVisa sponsorship offered

Core

Identify, research, and remediate conventional and novel AI agent threats to safeguard Apollo's internal surfaces and infrastructure.

Role type

Senior IC AI Security Researcher (Offensive Security)

Builds

Durable security controls, checks, tests, defaults, and detections for AI agent access and monitoring.

Domain

AI Security / Cybersecurity / Infrastructure Security

Deliverable

production ML models

Required skills

Threat modelling, red teaming, code reading, infrastructure evaluation, automation, systems-level thinking, adversarial test suite creation, CI/CD integration

Preferred skills

AI/ML systems security, LLM security, detection engineering, insider threat programs

Technologies

AI agents, CI/CD, cloud infrastructure

Responsibilities

Red-team internal software, infrastructure, and AI agent access controls; Design solutions for novel AI security threats; Track adversary tactics and translate intelligence into detections; Own findings through to deployed fixes and roll out durable controls.