Senior Software Architect, AI Systems and Networking
Core
Architecting and implementing high-performance communication and memory management libraries for distributed AI, driving hardware-software co-optimization with GPU/DPU/NIC/switch teams, and integrating networking capabilities into AI serving stacks.
Role type
Senior IC software architect (AI systems & networking)
Builds
High-performance communication libraries, memory management systems, and AI serving stack integrations
Domain
AI infrastructure, high-performance networking, GPU systems
Deliverable
production ML models
Required skills
High-performance networking (InfiniBand, RoCE, RDMA, NVLink, GPUDirect), C/C++/Rust systems programming, performance profiling, low-level debugging, ML systems concepts (transformers, KV cache, model parallelism, distributed training/inference)
Preferred skills
ML inference frameworks (vLLM, SGLang, TensorRT-LLM), storage networking (NVMe-oF, GPUDirect Storage, S3), Reinforcement Learning systems
Technologies
InfiniBand, RoCE, RDMA, NVLink, GPUDirect, vLLM, SGLang, TensorRT-LLM, NVMe-oF
Responsibilities
Architecting and implementing high-performance communication and memory management libraries; Driving hardware-software co-optimization with GPU, DPU, NIC, and switch teams; Profiling and optimizing data movement across GPU memory, system DRAM, NVMe, and network fabrics; Integrating networking capabilities into AI serving stacks; Contributing to and maintaining open-source projects, mentoring engineers, and prototyping experimental technologies
Seniority
Senior, hands-on IC
