SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Baseten powers mission-critical inference for leading AI companies like Cursor, Notion, and Abridge. The company recently raised $1.5B in Series F funding and is building the platform engineers use to ship AI products at scale.
You will lead the Storage Products team within the Runtime Fabric group, managing 5–10 systems engineers focused on building and operating storage infrastructure for AI inference workloads. The Runtime Fabric team is purpose-building container runtimes and storage layers specifically designed for AI, led by top containerd maintainers.
Key responsibilities include:
**Team Leadership:** Hire and develop systems engineers with storage and Linux expertise. Run planning and delivery cycles aligned with the Runtime Fabric roadmap. Provide coaching, feedback, and career development. Own on-call health and incident escalation.
**Technical Direction:** Guide the architecture of the Baseten Delivery Network (BDN)—a tiered caching system that makes cold starts 2–3x faster and eliminates thundering herd failures during burst scaling. Extend BDN from model weights to container images, training checkpoints, and deployment artifacts. Oversee on-host delivery mechanisms including lazy-loading snapshotters, EROFS, overlayfs, and block-level delivery (FUSE, ublk). Own end-to-end reliability: instrumentation from snapshotter initialization through first inference, cold-start targets, cache behavior, and safe rollouts. Make the delivery path work across heterogeneous clusters and cloud providers. Review designs and code; take on hands-on work where needed. Champion contributions back to containerd and the snapshotter ecosystem.
**Cross-Functional Partnership:** Serve as the storage point of contact across Baseten. Ensure model deployment, training, and platform teams have integration support. Optimize storage platform requirements with the infrastructure team. Manage dependencies with model deployment, training, and infrastructure teams. Work with the head of Runtime Fabric and product stakeholders to prioritize storage investments. Communicate progress, trade-offs, and incidents clearly.
REQUIREMENTS:
- Experience managing a team of 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
- Strong systems programming background in Go, Rust, and/or C/C++, with ability to engage credibly in code reviews and architectural discussions
- Working knowledge of the Linux storage stack: filesystems, page cache, block devices, and mounts
- Understanding of how container images are structured, stored, and delivered at scale
- Strong written and verbal communication skills; ability to influence without authority across teams
NICE TO HAVE:
- Contributions to containerd, snapshotter projects (stargz, soci, nydus, overlaybd), distribution/distribution, or related open-source projects
- Familiarity with lazy-loading snapshotters or peer-to-peer image distribution
- Experience with EROFS, FUSE, ublk, or io_uring
- Experience building or operating CDN, object storage, or large-scale caching infrastructure
- Experience running storage services on Kubernetes
