Senior Software Architect, AI Systems and Networking

What you'll do

• Architect high-performance communication and memory management libraries for distributed AI.
• Drive hardware-software co-optimization with GPU, DPU, NIC, and switch teams.
• Profile and optimize data movement across GPU memory, system DRAM, NVMe, and network fabrics.
• Integrate networking capabilities into AI serving stacks like vLLM and TensorRT-LLM.
• Prototype experimental technologies to evaluate their viability in production environments.

What we're looking for

• 12+ years of experience in systems software or networking with proven project ownership.
• MS, PhD, or equivalent experience in Computer Science, Engineering, or related field.
• Expertise in high-performance networking technologies like InfiniBand, RoCE, RDMA.
• Proficient in C/C++/Rust programming for system-level development and debugging.
• Knowledge of ML systems concepts including transformer architectures and distributed training.
• Understanding of ML inference frameworks such as vLLM, SGLang, TensorRT-LLM.
• Familiarity with storage networking technologies like NVMe-oF and GPUDirect Storage.