Zoox

Architect onboard GPU execution for perception, prediction, and planning workloads, including scheduling, multi-tenancy, isolation, and deterministic latency.Own the multi-year roadmap for reducing onboard compute per vehicle through latency and utilization budgets and optimization across models, runtimes, middleware, and hardware.Guide GPU and SoC selection, compute topology, memor

Lead design, implementation, and operation of training performance optimizations for VLM, VLA, and foundation-model training.Own the technical strategy and multi-quarter roadmap for reinforcement-learning frameworks and performance optimization.Profile and diagnose throughput bottlenecks across compute, compiler, framework, and cluster-networking layers.Partner with ML researchers,

Design, implement, and operate distributed training, mixed-precision, gradient-checkpointing, and GPU-kernel optimizations for VLM, VLA, and foundation-model training.Develop and optimize reinforcement-learning frameworks and performance for driving foundation models.Profile and debug training-throughput bottlenecks across compute, compiler, framework, and cluster-networking layers.

Design, develop, and maintain large-scale event-driven software-in-the-loop and hardware-in-the-loop tests and testing frameworks.Architect and manage continuous integration pipelines that automate regression test execution.Lead root cause analysis for complex system-level failures using log-mining scripts and visualization dashboards.Perform safety-requirement gap analyses and deve

Run and maintain benchmark pipelines and analyze results for routing errors and regressions across agent variants.Build and expand ground-truth datasets for evaluating agent outputs against known-correct answers.Identify validation gaps and support development of comprehensive evaluation infrastructure before release.Develop evaluation dimensions for label accuracy and structured-ou

Develop production-level, low-latency, memory-safe C++ and CUDA code for real-time perception algorithms on vehicle systems.Optimize multimodal sensor-fusion models, LLMs, VLMs, and other large-scale models using quantization, pruning, and mixed-precision inference.Architect model conversion and compilation pipelines using TensorRT for edge deployment.Perform model parity checking,

Own CI performance, cost efficiency, and reliability end-to-end across thousands of daily builds.Improve CI failure analysis, triage, developer support, and incident response using modern AI tools.Identify integration bottlenecks and resolve them at the platform level.Enable engineering teams to operate efficient and reliable CI systems.Set technical standards for CI construction an

Build and contribute to simulation, emulation, SIL, and HIL infrastructure for validating drive-control software.Design, develop, and test embedded software that translates planned trajectories into motor-torque, brake-torque, and steering-angle commands.Implement control-source arbitration and safety monitoring across trajectory execution and drive-control ECUs.Integrate supplier s

Own and extend the deck.gl-based map visualization library.Design and deliver 2D and 3D rendering capabilities for geospatial data, road networks, lane geometry, and proprietary road network structures.Partner with Cartography and Simulation teams to develop scalable visualization features.Improve rendering performance for large and complex map datasets.Improve code quality, documen

Contribute to the technical architecture and implementation of Zoox’s on-vehicle data systems.Design and develop reliable, high-performance systems for capturing, storing, retrieving, and transmitting vehicle data under strict real-time and resource constraints.Own complex technical problems from investigation through design, implementation, validation, and rollout.Collaborate acros

Develop firmware and LTE/5G cellular connectivity features across multiple hardware generations.Integrate proprietary cellular modem firmware and software stacks from chipset vendors into Zoox’s custom embedded Linux platform.Define and validate interfaces between RF-baseband, vendor protocol stacks, and the host system, including C/C++ Linux networking glue code.Prototype and evalu

Lead full-stack design and development of the Geofencer React/TypeScript application and Python backend services.Own geospatial workflows including versioned geofence editing, road-network annotation, drivable-area computation, connectivity validation, and Plan of Record releases.Integrate with the Zoox Road Network, S3 artifact pipelines, downstream fleet and mission systems, and M