ML Systems Engineer

We are technology lab building and operating purpose-built AI products for life sciences. Looking for one strong systems engineer to own the distributed stack that keeps our training, inference, and real-time agent execution reliable under production load. What you will actually do Design and scale high-throughput inference engines and distributed serving runtimes Optimize memory, GPU kernels, and inter-node communication for real hardware efficiency Build and harden secure code-execution sandboxes for agent workflows Work side-by-side with product engineers to keep frontier-model behavior stable in regulated environments What we are looking for Systems programming background (C++, Rust, or Python) and performance engineering experience Hands-on work with CUDA, Triton, Megatron-LM, SGLang, vLLM, or Ray Track record of shipping or maintaining high-performance ML infrastructure High ownership, fast iteration, zero tolerance for fragile shortcuts Compensation & location Direct access to NVIDIA hardware and software stack (DGX, CUDA, Triton, NCCL) NVIDIA / Lead Provider benefits — cloud credits, early hardware access Real ownership of production systems used by regulated life-sciences customers Small team, high signal Tokens and tokens #J-18808-Ljbffr