Software Engineer - Planner Frameworks Pipeline

About the role

Zoox is seeking an experienced Software Engineer to join a focused team within the larger Autonomy organization. The primary mission of this role is the design, construction, and operation of large-scale simulation pipelines. These pipelines are critical infrastructure, used to validate the behavior of the Zoox self-driving vehicle. The work is data and GPU intensive, relying on frameworks such as Ray.io and Kubernetes orchestrated across clusters. Given the scale and criticality of these validation systems, the role has a direct impact on the company's ability to iterate safely and rapidly on autonomy development. This is a hands-on position requiring a high degree of independence and ownership. The engineer will be expected to contribute to the architecture, reliability, efficiency, and capability expansion of the framework to support new use cases. While the role is primarily focused on off-vehicle pipelines, close collaboration with engineers developing on-vehicle algorithms and models is essential. The position requires staying close to the end users, the autonomy engineers, to understand the end-to-end requirements of the validation process.

Key facts

-

Location: USA

-

Engagement: Full-time

-

Compensation: USD 160,000 to 180,000

What you'll do

You will architect intake mechanisms designed to reliably collect and structure raw scenario information for simulation ingestion. The role involves configuring execution clusters using parallel frameworks to process demanding computational workloads with high efficiency. You will establish build processes responsible for packaging simulation code and dependencies, ensuring consistent deployment across all compute nodes. Implementation of review checkpoints is a core duty, requiring the development of systems that automatically verify correctness before large-scale test execution begins. You will orchestrate ship routines that coordinate the complex movement of data, asset generation, and result collection in timed operational cycles. Formulating partner dashboards is part of the work, visualizing key performance indicators related to simulation health and experiment status. The position requires designing monitor hooks capable of detecting anomalies in resource usage and alerting operators to potential failures proactively. Finally, you will document operational playbooks that standardize interaction with the simulation platform for various internal teams. You will analyze simulation results to identify edge case failures and feed learnings back into the planning algorithms. The role involves managing the lifecycle of simulation assets from initial configuration through final result archival.

Requirements

The candidate must bring a minimum of three years of experience managing complex software systems in production environments. Demonstrating advanced skill with Ray.io and Kubernetes is mandatory to effectively manage distributed tasks and cluster resources. A firm understanding of container images, networking setup, and storage patterns in cloud-based environments is required. A clear understanding of version control practices and their application to data, configuration, and model artifacts is essential for success in this role. The ability to read and interpret technical specifications is necessary to align pipeline development with system requirements. You must possess strong debugging capabilities to isolate and resolve issues within distributed pipeline workflows. Effective written communication skills are required for documenting processes and conveying technical details to cross-functional partners. The capacity to manage multiple priorities in a fast-paced environment is essential for meeting operational deadlines.

Nice to have

Prior experience with robotics or autonomous vehicles is not required but is preferred. Such experience provides a better grasp of the data and decision-making context inherent in the autonomy stack.

Practical notes

Please apply only if you are authorized to work in the United States and require no sponsorship now or in the future. The role is based in Foster City, California, requiring presence in the office during standard business hours. This position does not offer hybrid or remote work options. Travel is not expected as part of the core responsibilities.