Remote ML Infra Engineer – Large-Scale Model Serving

Mercor; San Francisco (CA); Remote; USD 180,000 - 230,000; Full time

Job summary

Mercor is seeking a hands-on ML systems engineer for a fully remote, 40-hour-per-week engagement. The role focuses on building and optimizing ML infrastructure, model serving, and accelerator performance across large language model workloads.

Collaboration with research and engineering teams is required to ensure high-quality training data and robust deployment pipelines. The position offers work with leading AI labs, exposure to TPU/accelerator ecosystems, and potential placement with trusted

Qualifications

• 2+ years of hands-on professional experience in ML systems, ML infrastructure, model serving, or accelerator performance engineering.

Responsibilities

• Design tasks across kernels, profiling, debugging and inference serving, including adversarial problems on accelerator code.

Skills

ML systems

ML infrastructure

model serving

accelerator performance engineering

JAX

PyTorch

Tools

Pallas

Triton

CUDA

CUTLASS

JAX

Kineto

Nsight

Job description

Mercor is seeking a hands-on ML systems engineer for a fully remote, 40-hour-per-week engagement. The role focuses on building and optimizing ML infrastructure, model serving, and accelerator performance across large language model workloads.

Collaboration with research and engineering teams is required to ensure high-quality training data and robust deployment pipelines. The position offers work with leading AI labs, exposure to TPU/accelerator ecosystems, and potential placement with trusted