Software Engineer - GPU Networking & Distributed Systems

• Make RDMA First-Class: work on integrating RDMA/RoCE/InfiniBand capabilities directly into our inference stack, moving beyond TCP/IP to unlock order-of- magnitude improvements in bandwidth and latency.
• Optimize Distributed Inference: implement and tune the networking layers necessary for efficient Disaggregated KV Cache Offload and WideEP, ensuring seamless communication across NVLink and InfiniBand for our MoE models.
• Enable Serverless-Grade Startup Speeds for LLMs: work deeply with checkpointing and storage mechanisms to enable sub-10-second startup for trillion-parameter models.
• Deep-Dive into Hardware: characterize and validate networking performance on bleeding-edge clusters (H100/H200, B200/B300, GB200/300 NVL72), writing acceptance tests that ensure our hardware delivers peak achievable throughput and minimal latency.
• Build Observability: design the tools that let us visualize packet flow, congestion, and effective bandwidth across the GPU interconnects, helping us diagnose complex distributed system behaviors.
• Optimize Kernels: work with communication libraries (NCCL, NVSHMEM) and potentially write custom communication kernels to overlap compute and data transfer., * Bleeding Edge Hardware: We are preparing to bring Blackwell (B200/B300) and then Rubin architectures online. You will be one of the first engineers in the industry optimizing networking for NVL72/GB300 racks.
• We go deep: We operate at every depth-from tuning hardware interconnects to writing custom communication kernels and designing distributed inference strategies-across the entire stack to deliver performance that goes far and beyond.
• High Impact: The networking optimizations you build will directly enable features that no one else in the industry has fully mastered yet, like seamless multi-node WideEP and instant model hydration.

• Deep experience with high-performance networking protocols (InfiniBand, RoCE v2) and understanding of the physics of data movement.
• Fluency in C++ or Python, bridging high-level logic and hardware. Deep understanding of the memory hierarchy in modern NVIDIA architectures (H100/Blackwell) and know how to optimize for it.
• Enjoy diving deep into code, writing custom C++/Python bindings, or debugging NVLink topology issues.
• Know when to use an off-the-shelf solution and when we need to build a custom solution because the upstream tools (like standard Kubernetes networking) are too slow for our needs., * Deep knowledge of NCCL, NVSHMEM, and UCX.
• Experience with GPUDirect Storage (GDS) or high-performance filesystems like Weka or 3FS.
• Familiarity with TensorRT-LLM, vLLM, or Sglang.
• Experience running low-level benchmarks to “qualify” new hardware clusters.

• Competitive compensation, including meaningful equity.
• 100% coverage of medical, dental, and vision insurance for employee and dependents.
• Generous PTO policy, including company-wide Winter Break (our offices are closed from Christmas Eve to New Year’s Day).
• Paid parental leave.
• Company-facilitated 401(k).
• Exposure to a variety of ML startups, offering unparalleled learning and networking opportunities.

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 enable companies operating at the frontier of AI to bring cutting-edge models into production. We’re growing quickly and recently raised our $300M Series E, backed by investors including BOND, IVP, Spark Capital, Greylock, and Conviction. Join us and help build the platform engineers turn to to ship AI products.

At Baseten, we are building the global operating system for distributed, heterogeneous AI hardware. We believe that as LLM and multi-modal workloads scale, the network is the computer. We are looking for foundational engineers to lead our GPU Networking efforts, making RDMA a first-class building block in our infrastructure and unlocking the next generation of distributed inference optimizations.