Jobs at Waymo

• Create Enterprise Risk Integration Processes: Design, develop, and implement scalable, repeatable processes and frameworks that synthesize information into a unified view of Automated Driving System safety risk.
• Drive Enterprise Risk Tooling Solutions: Define business requirements, data taxonomies, and wor...

• Define and execute the product roadmap for automated workflows that require network bandwidth in the depots (e.g. software downloads, data upload) which balances optimal use of charging & networking infrastructure, data demands and cost.
• Partner with data science and engineering to develop optimal techniques to manage these workflows

• Tackle ill-defined, ambiguous problems and reduce complex systems into tractable quantitative models.
• Develop statistical techniques that enable our evaluation pipelines to deliver better signals with fewer resources.

• Work with AI agents to create high performance low-level kernels in a Domain-Specific language for a custom ML accelerator
• Ensure functional correctness and numerical accuracy of kernels

• Critical backend systems - the platforms that power everything from trip matching to depot automation
• Horizontal functionality - eg. world simulation for regression testing and evaluation purposes

• Mine and curate dataset samples from large corpus of driving data
• Leverage large language models and world foundation models for reasoning, decision making and multi-modality generation

• Champion Product Quality & APQP/PPAP: Serve as the quality champion across the autonomous driving sensor development team (Cameras, Radars, Lidars), driving design methodologies and executing end-to-end quality plans (APQP and PPAP) from concept through mass production to ensure robust, reliable sensor modules that meet specifications.

• Understand the problem current LPM model is trying to solve along with its details
• Extend current reinforcement learning infrastructure and conduct experiments on our RL system. Tune parameters and compare with existing results

• Work with labeling engineers on iterating on compiler design and addressing user needs
• Experiment with different engineering approaches to determine best output for extensible future design

• Design and implement measures to increase the efficiency and decrease the cost of Fleet Response operations
• Partner with other teams at Waymo to find headroom in their shares of operational workload

• Research, design, and implement novel deep learning architecture, multi-task loss formulations, and preference/ranking objectives in Python and Jax for Waymo’s Large Selection model.
• Train and diagnose large-scale neural network using distributed TPU infrastructure, analyzing training dynamics, gradient conditioning and representation quality.

• Research, implement, and evaluate state-of-the-art generative models for planning and predictions using JAX
• Conduct machine learning models experiments

• Determine and author requirements and verification items for detection models that cover pedestrians near the Waymo vehicle.
• Collect and analyze data from existing logs and/or structured tests to test these requirements and identify false-positive clusters.

• Define, design, and execute strategic TA Operations roadmaps that streamline end to end recruitment workflows, scale operations, and enhance candidate experience.
• Serve as the strategic partner and system administrator for TA technology platforms (e.g. Greenhouse, Gem, ServiceNow), leveraging automation and AI solutions to scare service delivery.

• Design and implement state-of-the-art multi-modality (camera/radar/lidar/audio) and multi-task perception models. Potential project areas include:

3D object detection and tracking,
Open vocabulary detection applying world knowledge models,
3D occupancy detection,
Semantic segmentation,
Large-scale foundation models,
Pre-training and self-supervised learning through forecasting.

• Drive end-to-end software, electrical, and mechanical integration and bring-up of novel autonomous vehicle platform architectures and critical sub-systems.
• Lead root-cause investigation and resolution of complex multidisciplinary (ME, EE, and SW) issues spanning autonomous systems and base vehicle chassis components.

• Design and build infrastructure and tooling to diagnose software non-determinism across autonomous driving systems
• Investigate and resolve non-deterministic execution patterns across Waymo codebases

• Build Real-Time Network Monitoring & Diagnostics Infrastructure: Design and build Python infrastructure to enable real-time diagnostics and health monitoring for vehicle communication networks (CAN, CAN-FD, Ethernet) across multiple autonomous vehicle platforms.
• Develop Automated Verification Pipelines: Build automated verification and validation pipeline...

• Lead and manage the Behavior Test Engineering’s Collision Avoidance Testing Team, including hiring, setting OKRs, guiding work, and developing your report's careers
• Interface with key stakeholders from Planner, Perception, Systems Engineering and Safety Engineering executives on the Collision Avoidance Testing framework and desired AV behavior

• Design, implement, and benchmark parameter-efficient fine-tuning (LoRA / QLoRA) modules in JAX/Flax for multi-task Vision Transformer backbones
• Develop dual-level distillation pipelines (intermediate feature matching and task-head logit distillation) to mitigate multi-task regressions during large-scale data scaling