About Anthropic
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.
About the Role
At Anthropic, we're building frontier AI systems that require unprecedented levels of security and isolation. We're seeking a Staff Software Engineer specializing in container and VM security to help us design and implement robust sandboxing solutions that protect our AI infrastructure from untrusted workloads while maintaining performance and usability.
In this role, you'll be at the forefront of securing our compute infrastructure, working with cutting-edge virtualization and containerization technologies. You'll architect secure-by-default systems that leverage Linux kernel isolation mechanisms, design threat models for complex distributed systems, and build defenses that can withstand sophisticated attacks. Your work will be critical in ensuring that our systems remain secure as we scale to support increasingly powerful models and diverse use cases.
Responsibilities
- Design and implement secure sandboxing architectures using virtualization (KVM, Xen, Firecracker, Cloud Hypervisor) and container technologies (OCI containers, gVisor, Kata Containers) to isolate untrusted workloads
- Develop deep expertise in Linux kernel isolation mechanisms including namespaces, cgroups, seccomp, capabilities, and LSMs (SELinux/AppArmor) to build defense-in-depth strategies
- Create comprehensive threat models for our sandboxing infrastructure, identifying attack vectors and designing mitigations for container escapes, VM breakouts, and side-channel attacks
- Build and maintain security policies and configurations for multi-tenant cloud environments, ensuring strong isolation between different workloads
- Partner with infrastructure teams to implement secure-by-default patterns for deploying and managing containerized and virtualized workloads at scale
- Develop monitoring and detection capabilities to identify potential security breaches or anomalous behavior within our sandboxed environments
- Lead security reviews of new sandboxing technologies and provide guidance on their adoption within our infrastructure
- Mentor other engineers on secure coding practices and sandboxing best practices
- Contribute to our security incident response efforts, particularly for isolation-related security events
- Collaborate with research teams to understand the unique security requirements of AI workloads and develop appropriate isolation strategies
You may be a good fit if you:
- Have 8+ years of experience in systems security, with deep expertise in virtualization and containerization security
- Possess expert-level knowledge of Linux kernel isolation mechanisms and have experience implementing them in production environments
- Have a proven track record of securing untrusted workloads in cloud settings, including both public cloud and private infrastructure
- Are proficient in multiple programming languages (e.g., Go, Rust, C/C++, Python) with experience in systems programming
- Have hands-on experience with container runtimes (Docker, containerd, CRI-O) and orchestration platforms (Kubernetes)
- Understand hypervisor internals and have experience with VM security (QEMU/KVM, Xen, VMware, Hyper-V)
- Can design and articulate complex threat models for distributed systems
- Have experience with cloud provider security models and their isolation guarantees
- Thrive in ambiguous environments and can balance security requirements with performance and usability needs
- Communicate effectively with both technical and non-technical stakeholders about security risks and mitigations
Strong candidates may also have:
- Experience with microVM technologies (Firecracker, Cloud Hypervisor) and their security properties
- Knowledge of hardware-based security features (Intel TDX, AMD SEV, SGX) and their application to confidential computing
- Contributions to open-source security projects related to containerization or virtualization
- Experience with eBPF for security monitoring and enforcement
- Understanding of AI/ML workload characteristics and their unique security requirements
- Track record of identifying and responsibly disclosing security vulnerabilities in virtualization or container platforms
- Experience building security tooling and automation for large-scale infrastructure
- Background in formal verification or security research
Representative projects:
- Designing a multi-layered sandboxing architecture that combines VMs and containers to safely execute untrusted AI-generated code
- Implementing runtime security policies using seccomp, AppArmor, and SELinux to minimize container attack surface
- Building a threat detection system that identifies potential container escape attempts using eBPF and kernel audit logs
- Creating secure defaults and guardrails for Kubernetes deployments to prevent privilege escalation and lateral movement
- Developing automated security testing for our sandboxing infrastructure to continuously validate isolation properties
- Architecting network isolation strategies using CNI plugins and cloud-native firewalling to segment workloads
**Deadline to apply: **None. Applications will be reviewed on a rolling basis.
The expected base compensation for this position is below. Our total compensation package for full-time employees includes equity, benefits, and may include incentive compensation.
Annual Salary:
$320,000—$485,000 USD
Logistics
**Education requirements: We require at least a Bachelor's degree in a related field or equivalent experience.
Location-based hybrid policy:** Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices.
Visa sponsorship: We do sponsor visas! However, we aren't able to successfully sponsor visas for every role and every candidate. But if we make you an offer, we will make every reasonable effort to get you a visa, and we retain an immigration lawyer to help with this.
We encourage you to apply even if you do not believe you meet every single qualification. Not all strong candidates will meet every single qualification as listed. Research shows that people who identify as being from underrepresented groups are more prone to experiencing imposter syndrome and doubting the strength of their candidacy, so we urge you not to exclude yourself prematurely and to submit an application if you're interested in this work. We think AI systems like the ones we're building have enormous social and ethical implications. We think this makes representation even more important, and we strive to include a range of diverse perspectives on our team.
How we're different
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.
Come work with us!
Anthropic is a public benefit corporation headquartered in San Francisco. We offer competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space in which to collaborate with colleagues. Guidance on Candidates' AI Usage: Learn about our policy for using AI in our application process