Software Engineer, Sandboxing

Thinking Machines Lab•San Francisco, CA

3d•$300,000 - $350,000•Onsite

About The Position

Our models and agents increasingly need to run code, use tools, and take actions in the world — safely, reliably, and at scale. The Core Services team builds the sandboxing infrastructure that makes this possible: the isolated execution environments where models write and run code, browse, and interact with tools, both for our researchers during training and for external users building on Tinker. We're hiring a software engineer to help design, build, and operate this sandboxing platform. You'll work on the systems that isolate and constrain untrusted, model-generated code, and that scale to support thousands of concurrent executions across the company. This is foundational infrastructure: every research experiment and every product surface that lets a model take action depends on it being fast, secure, and dependable.

Requirements

Bachelor's degree or equivalent experience in computer science, engineering, or similar.
Proficiency in at least one backend language (we use Python or Rust).
Experience building or operating isolation or virtualization technology, such as containers, microVMs (e.g. Firecracker, Cloud Hypervisor), or sandboxed runtimes (e.g. gVisor, Kata Containers).
Solid grounding in Linux internals relevant to isolation: namespaces, cgroups, seccomp, capabilities, and networking.
Comfort operating across the stack and owning projects end-to-end.
Thrive in a highly collaborative environment involving many, different cross-functional partners and subject matter experts.

Nice To Haves

Experience securing systems that execute untrusted or adversarial code, including threat modeling and hardening against sandbox escapes.
Familiarity with running large-scale, multi-tenant infrastructure on Kubernetes or similar orchestration systems.
Experience with performance-sensitive systems programming and reducing cold-start latency for ephemeral compute.
Track record of contributing to open-source infrastructure or security tooling.
Interest in how AI agents use tools and code execution, and how that shapes the design of safe execution environments.

Responsibilities

Design, build, and operate sandboxed execution environments for running untrusted, model-generated code and tool calls at scale.
Improve isolation boundaries using technologies such as containers, microVMs, or gVisor-style kernels, balancing security against startup latency and throughput.
Build the scheduling, resource-management, and lifecycle systems that provision, reuse, and tear down sandboxes efficiently under heavy concurrent load.
Partner with researchers and Tinker's product team to expose sandboxing primitives that are simple to use and hard to misuse.
Instrument sandboxes for observability and abuse detection, and respond to novel escape or exploitation attempts as they're discovered.
Own reliability and performance of the sandboxing platform end-to-end, from API design down to the underlying virtualization layer.