← Back to jobs

MLOps Engineer, LLM Performance

Skills

cudadistributed systemsjaxllmmlopspytorchtritonPyTorch

Description

  • Remote MLOps Engineer role ($90–$120/hr) focused on LLM performance, accelerator kernels, profiling, distributed systems debugging, and high-throughput inference serving using CUDA, Triton, JAX, PyTorch, and TPUs. Full-time contract.

Perks and benefits

Work from home

Get similar jobs in United States by email

We'll email you when new jobs similar to this one appear.

Similar jobs

Explore more MLOps Engineer, LLM Performance jobs in United States.

Finding similar jobs…