Software Engineer, Sandboxing

EngineersOfAI; San Francisco (CA); Hybrid; USD 180,000 - 240,000; Full time

Job summary

Anthropic seeks a Sandboxing Engineer to design, build, and operate the sandboxing infrastructure that runs untrusted, model-generated code and agent workloads at scale.

You will work at the boundary of the Linux kernel, virtualization, and container ecosystems, collaborating with research, product, and security teams to ensure safe, fast, and scalable execution across Claude products and customers.

Qualifications

• Experience in Linux systems programming or kernel development.
• Proficiency in at least one systems language (Rust, C, C++, Go).
• Familiarity with virtualization/container isolation tech (KVM, QEMU, Firecracker, gVisor, runc).
• Understanding Linux resource management (namespaces, cgroups, scheduling, memory).
• Experience profiling and debugging system-level performance issues.
• Ability to learn unfamiliar codebases and ship practical, measurable outputs.
• Strong communication and commitment to safe, reliable systems.

Responsibilities

• Design, build, and operate sandboxing infrastructure for untrusted, model-generated code and agent workloads at scale.
• Improve sandbox startup time, density, throughput, including snapshot/restore, checkpointing, and warm pools.
• Strengthen isolation across compute, filesystem, and network, with egress controls and per-session credentials.
• Investigate and fix performance, reliability, and security issues at kernel, hypervisor, and container runtime levels.
• Build monitoring, tracing, and debugging tools to understand time/resource use inside a sandbox.
• Collaborate with researchers to support RL environments and evaluations requiring fast, reproducible isolated execution.
• Collaborate with product/platform engineers to expose sandboxes as dependable capabilities for Claude products and customers.
• Partner with security teams to threat-model the platform and test/harden/respond to escape scenarios.
• Work with cloud providers on hardware/platform features our workloads depend on.
• Share knowledge on systems programming and Linux internals, helping set team standards.

Skills

Systems language

Linux systems programming

Performance profiling

Communication

Adaptability

Ship practical solutions

Tools

KVM

QEMU

Firecracker

gVisor

runc

Job description

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

Every time Claude runs code, uses a computer, or works as an agent, it does so inside a sandbox. Our Sandboxing team builds the isolation layer behind that work. The same systems run the code Claude writes for users, the environments we train and evaluate models in, and the agents our customers deploy.

These workloads are untrusted by design, and there are a lot of them. Sandboxes need to start in milliseconds, hold up under adversarial code, and scale to a very large number of concurrent sessions. You will work at the boundary between the Linux kernel, virtualization, and the container ecosystem. You will partner with research, product, and security teams to make sure that safe and fast do not trade off against each other.

Key responsibilities

• Design, build, and operate the sandboxing infrastructure that runs untrusted, model-generated code and agent workloads at scale

• Improve sandbox startup time, density, and throughput, including snapshot and restore, checkpointing, and warm pools

• Strengthen isolation across compute, filesystem, and network, including egress controls and per-session credential handling

• Investigate and fix performance, reliability, and security issues at the kernel, hypervisor, and container runtime level

• Build the monitoring, tracing, and debugging tools that show where time and resources go inside a sandbox

• Work with researchers to support reinforcement learning environments and evaluations that need fast, reproducible, isolated execution

• Work with product and platform engineers to expose sandboxes as a dependable, well-designed capability for Claude products and customers

• Partner with security teams to threat-model the platform and to test, harden, and respond to escape and abuse scenarios

• Work with cloud providers on the hardware and platform features that our workloads depend on

• Share knowledge on systems programming and Linux internals, and help set technical standards for the team

Minimum qualifications

• Software engineering experience in Linux systems programming, kernel development, or another low-level area

• Strong programming skills in at least one systems language such as Rust, C, C++, or Go

• Working knowledge of virtualization or container isolation technologies such as KVM, QEMU, Firecracker, gVisor, or runc

• Understanding of Linux resource management, including namespaces, cgroups, scheduling, and memory management

• Experience profiling and debugging performance issues at the system level

• Ability to work in unfamiliar codebases and technical areas, and to ship practical solutions with measurable results

• Strong communication skills and a commitment to building safe, reliable systems

Preferred qualifications

• Experience building or operating a multi-tenant sandbox, serverless, or code execution platform

• Experience with microVMs, user-space kernels, or lightweight virtualization, including snapshot and restore

• Experience with OS-level security hardening, including seccomp, LSMs, and threat modeling of untrusted code

• Experience with eBPF and kernel tracing tools

• Experience with Kubernetes and cloud infrastructure at scale (AWS, GCP)

• Experience with network isolation, high-performance networking, or building egress proxies and policy layers

• Experience with sandboxes for AI agents, computer use, or reinforcement learning environments