Software Engineer, Storage Systems (Agent Infra)
Baseten · San Francisco
About this role
## Software Engineer, Storage Systems (Agent Infra) ### About Baseten Baseten powers mission-critical inference for the world’s most dynamic AI companies (like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma, and Writer). By uniting applied AI research, flexible infrastructure, and seamless developer tooling, we help frontier AI companies bring cutting-edge models into production. We’re growing quickly and recently raised our **$1.5B Series F**. Join us to help build the platform engineers rely on to ship AI products. ### The Role Storage decides how fast **agent sandboxes** start and how safely they share data. Agents need a filesystem that **thousands of sandboxes mount simultaneously**, with **strict isolation** and the **consistency** agents require. The **Agent Infra** team builds **Agent Drive**, a distributed filesystem that agent sandboxes mount over **FUSE**, plus the storage underneath it. The work uses **tiered caching**, **replication**, **content-addressed data**, and **Linux filesystem internals**. Baseten is building a cloud (not just using one), so storage is designed for **many tenants from day one**. The team is small and ownership is big—shipping in weeks and months. If you care about **page cache coherency**, **FUSE**, **replication protocols**, and **content-addressable storage**, we’d love to talk. ### Example Initiatives - Baseten + Blaxel: building the future of agentic infrastructure: https://www.baseten.co/blog/blaxel-is-joining-baseten-to-build-the-future-of-agentic-cloud/ - Baseten Sandboxes docs: https://docs.baseten.co/sandboxes ### Responsibilities - Design and implement core **Agent Drive** features: metadata replication, volume placement, garbage collection, and FUSE client behavior - Solve **multi-attach correctness**: cache coherency across many FUSE mounts, dentry/inode invalidation, write ordering, and crash consistency - Optimize **tail latency** on read/write paths (page cache strategy, writeback, prefetch, metadata RPC batching) - Build **tenant isolation** into the storage layer (quota enforcement, blast-radius containment, noisy-neighbor mitigation) - Own storage-side **sandbox startup and resume performance** - Build **durable block storage** for sandboxes alongside other Baseten storage teams - Add **observability** end-to-end and turn incidents into permanent fixes - Contribute upstream to the open-source storage projects we build on ### Requirements - Strong systems programming background in **Go, Rust, and/or C/C++**, comfortable reading kernel code - Deep understanding of **Linux filesystem and storage internals**: VFS, page cache, dentry/inode caches, FUSE, block I/O stack, fsync semantics, crash consistency - Hands-on experience building **distributed storage systems**, content-addressable storage, or large-scale caching infrastructure - Experience profiling **I/O, memory, and RPC bottlenecks** and optimizing **tail latency** in production - Ability to debug correctness bugs that appear under **concurrency** or **partial failure** - Move fast and enjoy owning problems end-to-end on a small team ### Nice to Have - Experience with distributed filesystem/object store (e.g., **JuiceFS, CephFS, S3-compatible storage**) or contributions to those projects - Knowledge of consensus/replication protocols (e.g., **Raft**, leader leases, quorum reads) - Experience with snapshot/clone/COW filesystem features - Experience operating multi-tenant storage with hard isolation requirements - F
Listing freshness
CronJobs last confirmed this listing 1h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.