Senior AI Benchmark Engineer - GPU Systems & Inference

IMR Soft Llc in Plano, TX is seeking an AI Senior Engineer to build and validate GPU infrastructure for distributed training and production inference. You will own the validation suite, optimize benchmarks, and deliver reports that help customers verify performance against reference architecture.

The role requires 5+ years of ML engineering with production GPU workloads, hands-on multi-node distributed training, and expertise in PyTorch DDP/FSDP, DeepSpeed, Triton, and vLLM.