Senior/Staff Software Engineer - Machine Learning & System Optimization

Zoox; Foster City (CA); On-site; USD 100,000 - 140,000; Full time

Job summary

Zoox in Foster City, California, is seeking a Machine Learning and System Optimization Engineer to innovate in developing multi-modality models for autonomous systems. You will manage system capacities and drive initiatives for efficient model inference.

The successful candidate will optimize and deploy complex models, focusing on real-time execution on edge devices. Key skills include model compression, CUDA programming, and experience with power-constrained vehicle systems.

Qualifications

• Hands-on experience with compressing and deploying complex models.
• Experience with large-scale models for constrained environments.
• Ability to write efficient CUDA code and optimize ML models.

Responsibilities

• Orchestrate system capacity for core perception models.
• Drive initiatives for efficient inference across perception stacks.
• Optimize machine learning models for real-time execution.

Skills

Model compression

CUDA programming

Machine learning optimization

Concurrent programming

Job description

The Perception team is pioneering the development of a multi-modality foundation model to drive the next generation of autonomous system intelligence.

As a Machine Learning and System Optimization Engineer, you will orchestrate and allocate overall system capacity to various core perception models running on-bot, as well as drive large initiatives that allow for more efficient inference by sharing various parts of the perception stack with one another.

You will focus on bringing highly efficient, production-ready large-scale models to our on-vehicle stack. We are looking for experts with hands‑on experience compressing, accelerating, and deploying complex models, including LLMs, VLMs, or foundation models, for power‑and thermal‑constrained vehicle SoCs.

In addition, you will optimize ML models, write custom CUDA kernels, and build highly concurrent inference code to ensure real‑time, deterministic execution on edge devices.