Engineering Manager Runtime - Storage at Baseten · LumiJobs

Responsibilities

Container runtimes were designed for general-purpose software workloads. AI inference is not a general-purpose workload.
Running large models at production scale exposes cracks in every layer of the container stack: runtimes unaware of GPU memory constraints, images that take minutes to pull when a model needs to scale to thousands of replicas, and isolation mechanisms that weren’t designed for the multi-tenant serving environments that production AI requires. The tools the industry has relied on for a decade weren’t built for this, and patching around those limitations at higher layers only goes so far.
Baseten owns the entire pipeline, from the moment a developer pushes a model to the moment a request gets a response. That vertical ownership means we can fix these problems at the root. The Runtime Fabric team is doing exactly that: purpose-building the container runtime and storage layers for AI inference workloads, led by some of the world’s top containerd maintainers.
As Engineering Manager for Storage Products on the Runtime Fabric team, you will lead the engineers who build and run the storage products behind that stack: the Baseten Delivery Network (BDN), which sits in the cold start path of every model on the platform, the snapshotters and filesystems that expose model weights and container images to a running container, and the storage that model deployment and training need next. The team is advancing the next generation of caching for inference workloads, from the origin tier to the GPU host. You will own reliability for the area as a measured outcome, report to the head of Runtime Fabric, and stay close to the code through design and code review. If you’ve managed systems engineers and have hands-on experience with caching, content-addressable storage, or distributed filesystems, we’d love to talk.
EXAMPLE INITIATIVES
How the Baseten Delivery Network (BDN) makes cold starts fast
Extending BDN from model weights to container image layers, training checkpoints, and deployment artifacts
Lazy-loading snapshotters and block-level delivery (EROFS, FUSE, ublk) so a container can start before the full image or model has arrived
Team Leadership and Culture
Hire and grow a team of 5 to 10 systems engineers with storage, caching, and Linux expertise
Run the team’s planning and delivery: scope work against the Runtime Fabric roadmap, set priorities, and ship on a predictable cadence
Provide regular coaching, feedback, and career development support to your direct reports

Engineering Manager Runtime - Storage

Responsibilities

Qualification

Required

Preferred

Benefits

Company

Baseten

More roles at Baseten