Software Engineer, ML Platform (ML Serving)

Core responsibilities:

• Build the off-vehicle inference service powering Foundational models (LLMs & VLMs) and models that improve rider experiences
• Lead the design, implementation, and operation of robust and efficient ML serving infrastructure for serving and monitoring ML models
• Collaborate closely with cross-functional teams including ML researchers, software engineers, and data engineers to define requirements and align on architectural decisions
• Enable junior engineers in the team to grow their careers by providing technical guidance and mentorship

This role enables innovations in ML and AI to make autonomous driving as seamless as possible, reducing the time from ideation to productionization of cutting-edge AI innovation for autonomous robotaxis that are safe, reliable, clean, and enjoyable for everyone.

Required qualifications:

• 4+ years of ML model serving infrastructure experience
• Experience building large-scale model serving using GPU and/or high QPS, low latency serving use cases
• Experience with GPU-accelerated inference using RayServe, vLLM, TensorRT, Nvidia Triton, or PyTorch
• Experience working with cloud providers like AWS and working with K8s

No specific benefits, compensation, or salary information mentioned in the job posting.

Zoox is on a mission to reimagine transportation and ground-up build autonomous robotaxis that are safe, reliable, clean, and enjoyable for everyone. They are developing the first ground-up, fully autonomous vehicle fleet and the supporting ecosystem required to bring this technology to market.