Sr. Staff Software Engineer – High Performance GPU Inference Systems

Candidates must have a proven ability to ship high-performance, production-grade distributed systems and maintain large-scale GPU production deployments. Deep knowledge of GPU architecture, OS internals, parallel algorithms, and HW/SW co-design principles is essential. Proficiency in systems languages such as C++ (CUDA), Python, or Rust, with fluency in writing hardware-aware code, is required. Candidates should be obsessed with performance profiling, GPU kernel tuning, memory coalescing, and resource-aware scheduling, and passionate about automation, testability, and continuous integration in large-scale systems. Comfort navigating across stack layers, from GPU drivers and kernels to orchestration layers and inference serving, is necessary. Strong communication, pragmatic problem-solving skills, and the ability to build clean, sustainable code are also key. An ownership-driven mindset is expected. Experience operating large-scale GPU inference systems, deploying and optimizing ML/HPC workloads on GPU clusters, hands-on experience with multi-GPU training/inference frameworks, and familiarity with compiler tooling are considered nice to have.