Frontier AI Security Engineer: Build Bold Defenses

Emploive; San Francisco (CA); On-site; USD 180,000 - 250,000; Full time

Job summary

Anthropic is hiring for a Security Labs engineer to lead high-risk, high-impact security projects. You will own projects end to end, build isolated security infrastructure, and collaborate with research and compute teams to validate workflows across model safety and cryptographic guarantees.

The role emphasizes deep specialization in firmware/hardware security, cryptography, or OS/hypervisor internals, with a track record of shipping secure systems in ambiguous environments.

Qualifications

• Deep expertise in at least one high-risk security domain such as firmware/hardware security, cryptography, OS/hypervisor internals, or formal methods.
• History of shipping secure systems or security research with measurable impact.
• Interest in AI safety/security and ability to operate in high-ambiguity environments.

Responsibilities

• Own Security Labs projects end to end, from scoping to prototype to hand-off or documentation.
• Stand up novel security infrastructure fast (isolated clusters, attestation chains, hypervisor/runtime work).
• Collaborate with research and infrastructure teams to validate security workflows.

Skills

Firmware security

Hardware security

Applied cryptography

OS/kernel/hypervisor internals

Formal methods & verification

Reverse engineering

High-assurance / cross-domain systems

Software engineering excellence

Job description

Anthropic is hiring for a Security Labs engineer to lead high-risk, high-impact security projects. You will own projects end to end, build isolated security infrastructure, and collaborate with research and compute teams to validate workflows across model safety and cryptographic guarantees.

The role emphasizes deep specialization in firmware/hardware security, cryptography, or OS/hypervisor internals, with a track record of shipping secure systems in ambiguous environments.