Software Engineer, Compute and Isolation
$165k - $330k • Remote • San Francisco • FullTime
Posted 5h ago
Job Location
San Francisco
Tech Stack
Remote Work Policy
Fully remote
Employment Type
FullTime
Categories
AI Infrastructure Engineer
About the job
Baseten powers mission-critical inference for leading AI companies, enabling them to bring cutting-edge models into production. We are building the platform engineers use to ship AI products, recently securing $1.5B in Series F funding. The Agent Infra team is responsible for the core virtualization layer that powers our agent sandboxes. This layer provides each agent with its own isolated microVM, capable of running code, calling tools, and maintaining state across long tasks. We are building a cloud infrastructure from the ground up, focusing on multi-tenancy and deep hardware integration.
Responsibilities
- Manage the microVM lifecycle for agent sandboxes, including start, stop, suspend, resume, snapshot, and fork operations.
- Develop and optimize custom guest kernels for sandbox environments.
- Tune host CPU and memory configurations to ensure optimal sandbox performance and safety on various hardware.
- Oversee host-level resource management and sandbox density on machines.
- Improve end-to-end startup and resume performance, from VM boot/restore to initial command execution.
- Manage the guest and host aspects of each sandbox, including identity, storage attachment, and secure network virtual devices.
- Design and implement isolation mechanisms for multi-tenant workloads, using the hypervisor as the primary security boundary.
- Debug virtualization and isolation issues at scale, spanning userspace, kernel, and hardware levels.
- Contribute architectural decisions and code to the open-source projects underpinning our infrastructure.
Requirements
- Hands-on experience with KVM, and familiarity with Firecracker, Cloud Hypervisor, or QEMU.
- In-depth understanding of Linux internals, including namespaces, cgroups, memory management, and the boot process.
- Experience building cloud infrastructure as a provider, rather than solely consuming cloud services.
- Proven experience in developing multi-tenant infrastructure with isolation as a core security feature.
- Strong systems programming skills in Rust and/or Go; C/C++ experience is also valued.
- Experience debugging performance and correctness issues across userspace and kernel boundaries.
- Ability to work in a fast-paced environment and take end-to-end ownership of problems within a small team.
Benefits
- Competitive compensation and meaningful equity.
- 100% coverage of medical, dental, and vision insurance for employees and dependents (U.S. only).
- Flexible Paid Time Off (PTO) policy, including a company-wide Winter Break.
- Paid parental leave.
- Fertility and family-building stipend.
- Company-facilitated 401(k) (U.S. only).
- Exposure to various ML startups for learning and networking.