The Role:We are looking for strong engineers with experience and interest in designing, building, and maintaining the novel, high-performance systems that make up our serverless platform. Specifically, you'll be working on the distributed object storage system that underpins every container image, volume, and checkpoint on Modal: hundreds of petabytes of data, replicated across multiple cloud object stores and a CDN, cached on local NVMe across a large fleet of workers in many datacenters, and shared peer-to-peer within each datacenter. You'll make cold starts feel local when the data is hundreds of milliseconds away, designing the caching, preloading, and peer-to-peer layers that hide object-store latency and keep public ingress off saturated uplinks. You'll own durability and cost at petabyte scale, from streaming and batch replication between origins, to garbage collection over billions of objects. You'll work across the stack, from local disk and page cache to distributed blob storage and garbage collection and you'll help shape what storage becomes next as we push storage closer to workloads.
Requirements:- 5+ years of experience writing high-quality production code
- Experience building high-performance distributed storage or caching systems at a large scale (the more challenges you've worked through, the better)
- Strong cloud skills, including deep familiarity with object storage (S3 or similar), CDNs, and their consistency, throughput, and cost characteristics
- Strong knowledge of low-level operating system foundations (Linux kernel, file systems, page cache, containers, etc.)
- Willingness to step into the thick of it with our on-call rotation and respond to production incidents
Nice-to-Haves:- Experience with replication, content addressing, and consistency models in multi-region or multi-cloud systems
- Experience operating storage systems at scale (petabyte-scale datasets, high-throughput read/write paths, large-scale garbage collection or data migration)
- Experience with data engineering at petabyte-scale.
- Prior experience with Rust
Key Things the Team Is Working On:- P2P sharing of data across workers within a single datacenter to dramatically reduce ingress
- Replicating data across multiple blob storage providers
- Automating garbage collection across hundreds of petabytes of data
- Deploying colocated storage clusters to datacenters to accelerate high-throughput customer workloads
