Anthropic • 📍 San Francisco / US Remote •
$240k - $320k USD
You will debug multi-node NCCL/RDMA collective stalls, write lock-free RadixAttention prefix routers in Tokio, and interface directly with custom FP8 CUDA kernels via C FFI.
#tonic • $197k-$266k USD Base
Tonic in Production Rust: Architecture & Open Roles
Native async gRPC client & server implementation over HTTP/2
1. Why Teams Deploy Tonic
Tonic is the standard Rust implementation of gRPC over HTTP/2, pairing `prost` Protobuf code generation with `hyper` transport and `tower` middleware. Distributed AI inference engines, vector databases like Qdrant, and disaggregated storage clusters use Tonic to stream millions of RPC frames per second between compute nodes.
2. Tonic Kernel & Memory Internals
Tonic compiles `.proto` definitions via `tonic-build` into strongly typed async traits. Bi-directional streaming RPCs map directly to `tokio_stream::Stream` pipelines, allowing LLM serving routers to stream generated token logits back to gateways as soon as a CUDA kernel finishes a forward pass. Engineers frequently customize Tonic's codec buffer allocation to avoid intermediate byte copying when deserializing large tensor payloads.
3. Tonic Interview & Hiring Bar
AI infrastructure teams at Baseten, Together AI, and Modal test candidates on gRPC load balancing, HTTP/2 keepalive tuning, and streaming backpressure across multi-node GPU clusters.
Open Tonic Engineering Positions (5)
Together AI • 📍 US / EU Remote •
$195k - $265k USD
Work directly on speculative decoding tree verification, PyO3 bindings for custom CUDA graphs, and Tonic bi-directional gRPC streaming backpressure.
Modal Labs • 📍 US / Americas Remote •
$190k - $260k USD
Optimize Linux cgroups v2 isolation, FUSE page-cache prefetching, and snapshot memory restoration across thousands of H100 nodes.
Qdrant • 📍 Europe / US Remote •
$175k - $235k USD
Design disk-backed HNSW graph traversal over Linux io_uring, tune Raft shard consensus rebalancing, and write hand-vectorized distance functions.
