Find a Job
Search open remote, hybrid and on-site roles.
Search open remote, hybrid and on-site roles.
Growing company
MLOpsJAXPyTorchLLM servingperformance profiling
the hiring platform seeks an MLOps engineer to contribute challenging technical tasks and evaluations across ML kernels, profiling, debugging and high-throughput LLM serving. This worldwide remote independent-contractor opportunity pays US$90–$120/hour and requires 40 weekday hours per week. H-1B and STEM OPT are not supported. Shared by an independent referrer who may receive a referral fee; the hiring team makes all decisions.
Write and evaluate technical tasks and solutions for ML systems. Work across accelerator kernels, performance profiling and debugging. Assess high-throughput LLM inference and serving. Produce technical rubrics and feedback.
At least two years of hands-on ML systems or infrastructure experience; candidates with more than three years are welcome. Experience with JAX and/or PyTorch. Accelerator performance or serving expertise. Availability for 40 weekday hours per week.
🔒 You are applying directly to this company. Leverage Jobs is not a recruiter in between. You will see the company name if you are shortlisted.
Growing company. Leverage 10x knows and checks every employer; the company name is shared with candidates who move forward in the hiring process.