Zoox

Software Engineer, ML Platform (ML Serving)

Zoox

Apply
24 days ago
Foster City, CA, USA
Mid Level / Senior
H1B Sponsor

Responsibilities

  • Build the off-vehicle inference service for foundational models and rider experience improvements.
  • Lead the design, implementation, and operation of ML serving infrastructure.
  • Collaborate with cross-functional teams to define requirements and architectural decisions.
  • Provide technical guidance and mentorship to junior engineers.

Requirements

  • 4+ years of experience in ML model serving infrastructure.
  • Experience with large-scale model serving using GPU and high QPS, low latency use cases.
  • Familiarity with GPU-accelerated inference tools like RayServe, vLLM, TensorRT, Nvidia Triton, or PyTorch.
  • Experience working with cloud providers such as AWS and Kubernetes.

Tech Stack

AWSKubernetesPyTorch

Categories

AI & MLBackendData Engineering