Inference & Model Serving Engineer

Role overview

Remote, full-time position for an Inference & Model Serving Engineer embedded within a Model Engineering team. The work centers on the production systems that host, optimize, and serve machine learning models reliably and at scale.

Responsibilities

- Design, build, and maintain infrastructure for model inference and serving - Optimize the latency, throughput, and reliability of model-serving pipelines - Collaborate with the Model Engineering team to support production ML workflows

Requirements

- Practical experience with model serving systems and inference pipelines - Comfort operating as part of a fully remote, distributed engineering team