Research Engineer, Frontier Red Team (Autonomy)
Is this job for you?
Build my CV Build your CV and see how well you match this role — and every other one.
The role
Design and build autonomous AI systems capable of tool use across diverse environments to serve as model organisms for safety research.
Create evaluation suites and training environments to understand and steer agent behavior toward safe, beneficial outcomes.
Develop defensive agents that detect, disrupt, or outcompete adversarial AI in realistic scenarios.
Interface language models with hardware platforms (e.g., robotics, cyber-physical systems) to study risks and defenses.
Translate technical findings into compelling demonstrations and artifacts for policymakers and the public.
Collaborate with external cybersecurity, national security, and AI safety experts to scope and validate research directions.
Create evaluation suites and training environments to understand and steer agent behavior toward safe, beneficial outcomes.
Develop defensive agents that detect, disrupt, or outcompete adversarial AI in realistic scenarios.
Interface language models with hardware platforms (e.g., robotics, cyber-physical systems) to study risks and defenses.
Translate technical findings into compelling demonstrations and artifacts for policymakers and the public.
Collaborate with external cybersecurity, national security, and AI safety experts to scope and validate research directions.
See the full job post
Responsibilities, requirements, skills and benefits — create your free account.
Already have an account? Log in
Similar openings
Other roles that could suit you.