The Architecture & ML Integration (AMI) team sits within SIML and focuses on horizontal, cross-cutting challenges spanning Waymo's end-to-end system. Our mission is to enable rapid evolution towards an ML-first architecture that is modular, flexible, and easy to experiment with. We do this by improving onboard software architecture, system debuggability, and developer experience through better API designs and comprehensive pipelines. The AMI team drives the convergence of Planner and Perception systems and tackles critical shared infrastructure components

You will:

• Have 8+ years of professional software development experience on large scale products
• Lead the software architecture and infrastructure development for onboard model consolidation across many onboard subsystems.
• Design and build an onboard framework to support flexible and efficient model integration and inference in Waymo’s onboard and simulation environments.
• Spearhead the alignment and unification of model’s data generation subsystem between model training data preparation and model inference.
• Develop Simulation solutions to enable robust testing and efficient evaluation/validation to enable good developer experience for consolidated model development.
• Embedded deeply with model teams to drive the productionization of unified models.
• Establish new software development best practices and technologies to accelerate model development and releases.

You have:

• BS/MS in Comp Sci, EE, Robotics, Physics, Math, or related field (or equivalent experience)
• Extensive experience designing and building large-scale, high-performance C++ software architecture for mission-critical systems or ML inference.
• Proven track record of leading complex, cross-functional engineering projects as a technical lead.
• Deep understanding of ML deployment, inference frameworks, and associated developer tooling.
• Good communication and collaboration skills working with cross-org partner teams

We prefer:

• Master's or PhD in Computer Science, Machine Learning, Robotics, or a related field.
• Experience with data pipelines and feature extraction for machine learning models.
• Prior experience in the autonomous driving industry, particularly focusing on onboard compute, perception, or planning systems.
• Experience with hardware accelerators (e.g., TPUs, GPUs) and ML models inference in edge/onboard environments.

Waymo's central platform and product for visual debugging, telemetry, and triage provides teams across the company (including Perception, Behavior, and Simulation) with 3D and data visualization tools, using a C++ and TypeScript framework to integrate domain-specific visualizations into a single tool. The backend processes and streams 4D (3D + time) time-series logs, real-time telemetry, and simulation data. In this L6 role, you will own the C++ server infrastructure and concurrent data streaming pipelines. You will design C++ abstractions to load and process fleet logs, optimize Borg and RPC performance, and build APIs that let engineers and automated evaluation pipelines analyze driving data.

You will:        
•    Build and maintain concurrent C++ backend services (Borg/Boq RPC servers) that stream time-series and sensor data to the client.    
•    Scale C++ data delivery abstractions for offboard storage (CNS, Spanner) and WebRTC streams.    
•    Optimize latency and throughput using log-sampling, payload post-processing (deduplication, timeline merging), and async C++ services.    
•    Build backend APIs for automated callers (triage bots, evaluation executors) to render driving scenes.    
•    Plan technical roadmaps and own the scaling, security, and performance isolation of the offboard data infrastructure.    
•    Mentor engineers, review system designs, and establish systems-level C++ best practices.    

You have:        
•    Bachelor's degree in Computer Science, a related technical field, or equivalent practical experience.    
•    5 years of software development experience in C++.    
•    Experience with systems programming, including multi-threading, concurrency, memory efficiency, and profiling.    
•    Experience building high-throughput distributed systems, RPC services, or time-series data pipelines.    
•    Experience leading technical designs and mentoring engineers on complex, multi-quarter projects.    

We prefer:        
•    Experience with Google-internal infrastructure (Borg, Boq, Stubby/gRPC, CNS, and Spanner).    
•    Experience developing backend systems for video/image rendering, WebRTC, or developer tools.    
•    Familiarity with autonomous vehicle data formats (RoadGraph, sensor logs, and trajectory prediction outputs).    
•    Familiarity with web client architectures (Angular, TypeScript) to design client-server APIs.    
•    Experience with TDD, performance profiling, and integration testing.    

Waymo's Compute Team is tasked with a critical and exciting mission: We deliver the compute platform responsible for running the fully autonomous vehicle’s software stack. To achieve our mission, we architect and create high-performance custom silicon; we develop system-level compute architectures that push the boundaries of performance, power, and latency; and we collaborate closely with many other teammates to ensure we design and optimize hardware and software for maximum performance. We are a multidisciplinary team seeking curious and talented teammates to work on one of the world’s highest performance automotive compute platforms.

This role follows a hybrid work schedule and you will report to a Silicon Engineering Lead

You will:

• Partner with design and architecture teams to translate hardware specifications into comprehensive, scalable verification plans
• Drive the development of testbenches, reference models, and stimulus to validate mission-critical functionality and performance
• Architect and enhance verification environments, contributing to shared tools and reusable methodologies across the organization
• Evaluate, integrate, and verify third-party Verification IP (VIP) to accelerate the development cycle
• Define and analyze coverage metrics (functional and code) to ensure design readiness and closure
• Advocate and establish verification best-practices

You have:

• 3+ years of experience building and maintaining complex testbenches using UVM/SystemVerilog
• Proven track record with constrained-random generation, functional coverage, and SVA (SystemVerilog Assertions)
• Deep understanding of complex digital logic and the ability to debug intricate hardware/software interactions
• Proficiency in Python for developing scalable automation frameworks, data analysis tools, and regression management suites
• Excellent verbal and written communication skills, ability to collaborate with cross-functional teams
• Strong analytical skills in root-causing failures across RTL, testbench, and environment layers

We prefer:

• Experience spanning initial specification through post-silicon bring-up and validation
• Familiarity with power-aware verification (UPF), formal verification, or hardware-software co-validation
• Domain expertise in ML accelerators, high-speed interconnects (NoCs), or high-bandwidth memory
• Experience with C/C++ for reference model development and enhancement
• Hands-on experience with industry-standard interfaces such as PCIe Gen 5/6, DDR5, or Ethernet
• Interest or experience in leveraging Generative AI and LLMs to accelerate verification workflows, such as automated testbench generation, documentation, or failure log analysis

The Planner Evaluation team works on one of the key challenges in autonomous driving: measuring and improving the quality of the software that drives the car. We are looking for experienced data-minded software engineers and data scientists to help us improve how we characterize and evaluate changes to the Onboard software stack (Planner, Perception, etc). If you are passionate about autonomous vehicles and how to use rich, complex data to drive decision making, this is the role for you!

This role follows a hybrid work schedule and reports to an Sr. Engineering Manager.

You will:

• Develop signals to measure the performance and driving qualities of the Waymo driver, using a range of techniques including statistics, math, physics, algorithms and machine learning.
• Use simulation creatively and mine real world driving logs to measure  driving performance.
• Design and implement methods to make a stronger connection between onboard software changes and simulated outcomes.
• Champion code health and best practices in a large and complex code base.
• Analyze data and make recommendations on how to improve metric quality and interpretability.
• Collaborate with other engineers, data scientists, statisticians and the leadership team to deliver evaluation products and help make data driven decisions.

You have:

• BS in Computer Science, Robotics, Statistics, Physics, Math or another quantitative area
• Strong self-motivation to navigate complex systems and pursue open-ended problems to completion
• 4-7 years of industry experience with
  
  • Navigating and modifying a large code base containing a variety of languages, such as C++, Python and SQL
  • Performing statistical analyses
  • Building data processing pipelines
  • Writing, reviewing, and merging code following industry standards for code health and maintainability
  • Quant/data fluency is a top requirement

We prefer:

• Experience coding in C++
• Experience with ML
• Experience with A/B experiment infrastructure
• Experience building and validating metrics to measure quality in complex systems
• Exposure to ad-hoc data analysis tools for rapid modeling and prototyping
• Experience working in the AV industry

#LI-Hybrid