Security Engineer, Offensive Security

Remote-Friendly (Travel-Required) | San Francisco, CA | Seattle, WAFull-TimeMid-levelSoftware Engineering

You will be redirected to the company career page

Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.

The Security Engineering team's mission is to safeguard our AI systems and maintain the trust of our users and society at large. Whether we're developing critical security infrastructure, building secure development practices, or partnering with our research and product teams, we are committed to operating as a world-class security organization and keeping the safety and trust of our users at the forefront of everything we do.

Conduct red and purple team engagements simulating advanced threat actors across our cloud infrastructure, endpoints and bare metal deployments.
Penetration test specific, high value deployments.
Contribute to AI-assisted security testing tooling and workflows.
Work cross functionally with other security and engineering teams, particularly on AI-specific attack scenarios.
Document and present findings to technical and executive audiences, translating attack narratives into actionable risk insights that inform security roadmaps.

5+ years of hands-on experience in red teaming and offensive security operations
Deep expertise in at least two of: macOS security, Linux Security, Cloud security (GCP/AWS/Azure), Kubernetes, CI/CD pipelines
Track record of discovering novel attack vectors and chaining vulnerabilities creatively
Experience conducting adversarial simulations against well-defended environments
Strong engineering skills (Python, Go, or similar)
Ability to write clear findings that drive action, helping teams understand risk and prioritize fixes
Collaborative approach, working in close collaboration with the blue team

Prior work at organizations with state actor threat models
Interest in AI safety and how security engineering contributes to responsible AI developments
Background testing AI/ML systems or agentic workflows
Familiarity with detection engineering and SIEM/EDR platforms from the defensive side
Experience with data center security or hardware-based attacks
Deadline to apply: None. Applications will be received on a rolling basis.
The annual compensation range for this role is listed below.
For sales roles, the range provided is the role’s On Target Earnings ("OTE") range, meaning that the range includes both the sales commissions/sales bonuses target and annual base salary for the role.

We believe that the highest-impact AI research will be big science. At Anthropic we work as a single cohesive team on just a few large-scale research efforts. And we value impact — advancing our long-term goals of steerable, trustworthy AI — rather than work on smaller and more specific puzzles. We view AI research as an empirical science, which has as much in common with physics and biology as with traditional efforts in computer science. We're an extremely collaborative group, and we host frequent research discussions to ensure that we are pursuing the highest-impact work at any given time. As such, we greatly value communication skills.
The easiest way to understand our research directions is to read our recent research. This research continues many of the directions our team worked on prior to Anthropic, including: GPT-3, Circuit-Based Interpretability, Multimodal Neurons, Scaling Laws, AI & Compute, Concrete Problems in AI Safety, and Learning from Human Preferences.