MLOps Engineer, LLM Systems (Serving, GPU Kernels, Profiling)

Gridnaut Recruiting is hiring a remote MLOps Engineer, LLM Systems (Serving, GPU Kernels, Profiling) contractor (pay $90–$120/hr). Contribute to frontier AI research and evaluation work. Ideal candidates: Have 2+ years of hands-on professional experience in ML systems, ML infrastructure, model serving, or GPU/accelerator performance engineering.; Have practical experience in GPU kernels, performance profiling/trace analysis, debugging distributed workloads, or serving large language models at scale.; Have production experience with JAX and/or PyTorch; framework-level depth is a strong plus.; Be familiar with modern accelerators such as A100, H100, B200 or TPU and reason about throughput, latency and memory trade-offs.; Engage reliably for at least 40 hours per week during weekdays.; Have strong written communication and explain complex technical decisions clearly..