Realtime On-Device & GPU Inference Architect

Genesis AI is building cutting-edge distributed ML inference systems for robotics with real-time capabilities. You will design low-latency pipelines for on-device deployment and develop high-performance kernels in CUDA, Triton, and related stacks to push throughput and minimize latency.

The role requires deep expertise in distributed systems and ML infrastructure, with production-grade Python and strong system languages knowledge.