8 hours ago
Base Salary
$165k - $330k/yr
Responsibilities
- Own the microVM lifecycle, including startup, shutdown, suspension, resumption, snapshotting, and forking.
- Build and tune custom guest Linux kernels and optimize host CPU, memory, resource density, storage, and networking.
- Design guest and host sandbox identity, virtual devices, and multi-tenant isolation where the hypervisor is the security boundary.
- Improve boot and snapshot-restore performance through the first command executed in a sandbox.
- Debug virtualization, isolation, performance, and correctness issues across userspace, kernels, and hardware.
- Contribute architecture decisions and code to the open-source virtualization projects used by the platform.
Requirements
- Hands-on experience with KVM and at least one of Firecracker, Cloud Hypervisor, or QEMU.
- Deep understanding of Linux internals, including namespaces, cgroups, memory management, and the boot path.
- Experience building cloud infrastructure as a provider, including multi-tenant compute customers run.
- Experience building infrastructure where isolation is a security boundary.
- Strong systems programming experience in Rust and/or Go; C and C++ are also welcome.
- Experience debugging performance and correctness issues across userspace and kernel boundaries.
- Preferred experience includes contributions to KVM, Firecracker, Cloud Hypervisor, QEMU, rust-vmm, or the Linux kernel; Xen; container runtimes and sandboxing; VM snapshot and restore; bare-metal virtualization; sandbox or serverless runtimes; and Linux performance tooling.
Benefits
- Competitive compensation with meaningful equity.
- 100% U.S. coverage of medical, dental, and vision insurance for employees and dependents.
- Flexible paid time off and a company-wide Winter Break from Christmas Eve through New Year's Day.
- Paid parental leave.
- Fertility and family-building stipend through Carrot.
- Company-facilitated U.S. 401(k).
- Exposure to a variety of ML startups and related learning and networking opportunities.
About Baseten
Baseten builds an AI inference platform that provides tooling, infrastructure, and hardware to deploy, scale, and serve machine-learning models in production. The company sells managed model serving and developer tooling to software teams at AI product companies, with customers including Notion, Abridge, Writer, and Cursor. Privately held and headquartered in San Francisco, it focuses on high-availability, globally distributed inference for production workloads.