Engineering Manager Runtime Storage
Baseten is an AI inference platform for deploying, optimizing, and scaling custom, open-source, and fine-tuned models in production.
Funding history
About Baseten
Baseten provides model runtimes, inference infrastructure, developer workflows, and deployment options including managed cloud, self-hosted, and hybrid environments.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will lead engineers building and operating storage products for model delivery, including the Baseten Delivery Network, snapshotters, filesystems, and related deployment and training storage. You will set priorities, guide technical architecture, manage reliability and on-call health, review designs and code, and coordinate dependencies with deployment, training, infrastructure, and product stakeholders.
Requirements
- Experience managing engineers in systems, infrastructure, or storage contexts, including hiring and performance management
- Hands-on background in distributed storage systems, content-addressable storage, or large-scale caching infrastructure
- Systems programming experience with Go, Rust, and/or C/C++
- Working knowledge of Linux storage, including filesystems, page cache, block devices, and mounts
- Understanding of container image structure, storage, and delivery at scale
- Written and verbal communication skills and ability to influence across teams
Responsibilities
- Hire and develop a team of systems engineers
- Plan, prioritize, and deliver work against the Runtime Fabric roadmap
- Provide coaching, feedback, and career development support
- Own on-call health, escalation paths, and incident follow-through
- Guide the architecture and evolution of the Baseten Delivery Network
- Shape storage products for model weights, container images, training checkpoints, and deployment artifacts
- Oversee lazy-loading snapshotters, filesystem layouts, and block-level delivery
- Own delivery-path reliability, instrumentation, performance targets, and safe rollouts
- Support delivery across heterogeneous clusters and cloud providers
- Review designs and code and perform hands-on work when needed
- Contribute to containerd and the snapshotter ecosystem
- Act as the storage point of contact across the organization
- Manage storage-related dependencies, interfaces, and timelines
- Communicate progress, technical trade-offs, and incidents to leadership
Benefits
- Equity
- 100% coverage of medical, dental, and vision insurance for U.S. employees and dependents
- Flexible PTO
- Company-wide Winter Break
- Paid parental leave
- Fertility and family-building stipend through Carrot
- Company-facilitated 401(k) for U.S. employees