Engineering Manager (Runtime - Storage)

Baseten; United States; Remote; USD 190,000 - 240,000; Full time

Benefits offered by this job

Remote-first culture

Home-office stipend $1k

Unlimited PTO

Healthcare coverage

Parental leave

401(k)

Learning & development budget

Job summary

Baseten is seeking an Engineering Manager for Storage Products within the Runtime Fabric team. You will lead the engineers responsible for the Baseten Delivery Network (BDN), caching improvements, and storage delivery paths. You will own reliability, guide design, and stay hands-on where needed.

You will hire and develop a team of 5–10 engineers, set delivery priorities, and manage on-call reliability while working across Baseten’s cloud and deployment stacks.

Qualifications

• Experience leading a Systems/Storage team in a large-scale infra
• Hands-on with caching and content-addressable storage
• Proven ability to design reliable storage paths and delivery systems
• Contributions to containerd/snapshotter ecosystems are a plus

Responsibilities

• Lead and grow a team of 5–10 systems engineers with storage, caching, and Linux expertise
• Own planning and delivery against the Runtime Fabric roadmap
• Provide coaching and career development to reports
• Own on-call health for team services and incident follow-through
• Guide architecture and evolution of Baseten Delivery Network (BDN)
• Extend BDN to include model weights, container images, and deployment artifacts
• Oversee on-host delivery components (snapshotters, EROFS, overlayfs) and block delivery
• Ensure end-to-end reliability and instrumentation of the delivery path
• Collaborate cross-functionally with model deployment, training, and infra teams
• Represent Baseten in containerd/snapshotter communities

Skills

Team leadership

Storage systems

Caching

Go/Rust/C/C++

Linux knowledge

Open-source contributions

Tools

containerd

snapshotters (stargz, soci, nydus, overlaybd)

FUSE

EROFS

io_uring

Kubernetes

Job description

• 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
• 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
• Own on-call health for the team’s services, including escalation paths and follow-through on incidents
• Technical Direction
• Guide the architecture and evolution of the Baseten Delivery Network: the tiered caching and weight delivery product that makes cold starts 2-3x faster and eliminates thundering herd failures during burst scaling events
• Shape storage products tailored to Baseten’s workloads: extend BDN from model weights to container images, training checkpoints, and deployment artifacts, and define the interfaces that model deployment, training, and customers use to reach them
• Oversee the on-host side of delivery: lazy-loading snapshotters, EROFS and overlayfs layouts, and block-level delivery (FUSE, ublk) for multi-gigabyte files
• Own reliability of the delivery path as a measured outcome: end-to-end instrumentation from snapshotter initialization to first inference request, targets for cold start and cache behavior, tolerance for failing upstream registries and object stores, and safe rollout of changes to a path every customer depends on
• Make the delivery path work across heterogeneous clusters and cloud providers, each with its own object store and network
• Review designs and code across the area, and take on hands-on work where it unblocks the team
• Champion the team’s contributions back to containerd and the snapshotter ecosystem alongside the maintainers on the Runtime Fabric team
• Cross-Functional Partnership
• Act as the point of contact for storage across Baseten, ensuring model deployment, training, and platform teams have the integration support they need
• Optimize requirements for the underlying storage platforms with the infrastructure team: object storage, local NVMe and block storage, and network bandwidth per cluster, so that capacity and provider decisions account for what the delivery path needs
• Manage the team’s dependencies in both directions: sequence work that model deployment, training, and infrastructure teams block on, and negotiate interfaces and timelines with the teams and upstream projects the storage path depends on
• Work with the head of Runtime Fabric and product stakeholders to prioritize storage investments based on customer impact and infrastructure reliability
• Communicate team progress, technical trade-offs, and incidents clearly to the team and to leadership

Benefits

• Remote-first work environment. The Baseten team is welcome to work from wherever they want; fully remote, in our San Francisco office, or a mix of both. Today, our team (including our founding team) is spread across the United States, Canada, and Armenia. We provide a $1,000 stipend for you to make your home-office comfortable and productive
• Regular in-person team summits. We get together as a team three times a year to plan, workshop, and most importantly, get to know each other better
• Unlimited PTO. We ask that everyone take at least 4 weeks of vacation. And we have a company-wide break between Christmas and New Year’s Day
• Full healthcare coverage. Medical, dental and vision insurance for you and your family
• Paid parental leave. 16-weeks fully paid parental leave (adoptive and non-birth parents included) and flexibility with schedules while returning to work
• Company-sponsored 401(k) for you to contribute to
• Learning and development budget. We encourage you to take classes, attend conferences, and invest in your craft and we’ll cover expenses to make it happen

Strong written and verbal communication skills, with the ability to influence without authority across teamsExperience managing a team of engineers in a systems, infrastructure, or storage context, including hiring and performance management [TODO: confirm whether a tech lead stepping into management qualifies]Understanding of how container images are structured, stored, and delivered at scaleHands-on background in distributed storage systems, content-addressable storage, or large-scale caching infrastructureWorking knowledge of the Linux storage stack: filesystems, the page cache, block devices, and mountsStrong systems programming background in Go, Rust, and/or C/C++, with the ability to engage credibly in code reviews and architectural discussionsContributions to containerd/containerd, snapshotter projects (stargz, soci, nydus, overlaybd), distribution/distribution, or closely related open-source projectsFamiliarity with lazy-loading snapshotters or peer-to-peer image distributionExperience with EROFS, FUSE, ublk, or io_uringExperience building or operating CDN, object storage, or large-scale caching infrastructureExperience running storage services on Kubernetes