Principal Architect – Simulation Engine (Physical AI)
and Performance – Simulation on GPU clusters and cloud (Kubernetes, Slurm, Ray, CUDA) with a record of improving throughput..., Bazel or CMake, CI/CD for large monorepos; Rust or CUDA a plus. Architecture Leadership – Served as architectural...
Senior Inference Engineer
access paQerns. CUDA, HIP, Triton, or CUTLASS proficiency. KV and prefix caching: Paged KV storage, fragmentation, cache... and debug CUDA C++ or HIP kernels Hands-on GPU profiling and performance optimization Preferred: Custom GPU kernel...
Uniphore ⚡ ⚡ Sat, 17 Oct 2026 00:40:17 GMT