Staff Software Security Engineer: Frontier AI Research

EngineersOfAI; New York (NY); On-site; USD 180,000 - 240,000; Full time

Job summary

Anthropic is seeking generalists with rare depth to join Security Labs, tackling high-risk, high-value security projects. You will contribute across firmware, cryptography, OS internals, and formal methods, owning initiatives from inception to production hand-off.

Projects aim to harden AI systems, with a fast iteration pace and outcomes that may not always land. You will work with a scrappy, ambitious team focused on meaningful security breakthroughs.

Qualifications

• Strong software engineer with deep specialization in at least one area.
• Experience in firmware or hardware security, applied cryptography, or OS internals.
• Ability to work on high-risk, exploratory research with uncertain outcomes.
• Willingness to own projects end to end.

Responsibilities

• Own Security Labs projects end to end.

Skills

Software engineering

Firmware security

Applied cryptography

OS kernel internals

Formal methods

Reverse engineering

Cross-domain security

Job description

Anthropic is seeking generalists with rare depth to join Security Labs, tackling high-risk, high-value security projects. You will contribute across firmware, cryptography, OS internals, and formal methods, owning initiatives from inception to production hand-off.

Projects aim to harden AI systems, with a fast iteration pace and outcomes that may not always land. You will work with a scrappy, ambitious team focused on meaningful security breakthroughs.