Staff Machine Learning Engineer, ML Performance & Optimization

Waymo has successfully deployed self-driving cars in real-world environments; now, our imperative is to scale this capability. Scale is driven by large models and data, and we are moving to ever-larger models which generalize by being trained on more data. To achieve this, we're focused on optimizing model inference and training, ensuring these advancements gracefully generalize across multiple platforms.

In this role, you'll work embedded in an ML Engineering and Modeling team, working hand-in-hand to drive scale and multi-platform support of models. This role requires to follow the latest developments in efficient ML and bring those innovations to Waymo’s production systems.

In this hybrid role, you'll report to a Technical Lead Manager. 

• Optimize neural model architectures and systems for high performance on multiple GPU and TPU platforms (e.g., onboard vs simulation platform)
• Optimize neural model performance and overall  system performance for systems with hard real-time constraints (Waymo’s onboard system)
• Develop post-training algorithms (e.g., quantization), low-level optimizations (e.g., kernel optimization), etc. for improving inference speed and reducing inference memory consumption on modern GPU and TPU architectures
• Develop new neural model architectures (e.g., sparse architectures), decoding strategies (e.g., speculative decoding), etc. for improving  inference performance on modern GPU and TPU architectures
• Optimize model training speed and efficiency for large models (often memory bound) and for fine-tuning (often i/o bound)
• Collaborate with ML infra teams (inference frameworks, training frameworks), Onboard hardware and Simulation teams, and Alphabet’s research teams

• Master’s degree or PhD in Computer Science, Engineering, or a related technical field
• 3+ years of experience in software development for neural model inference or neural model training, and 1+ years experience with neural model inference and training optimization on modern GPU/TPU architectures
• 5+ years experience in software development for real-time systems, ideally experience with real-time systems running on device (e.g., Waymo’s onboard system)
• Proficiency in C++, Python, and modern deep learning toolkits like PyTorch or JAX
• Passionate about low-level neural net optimization and willingness to learn new architectures and tools
• Deep understanding of latency and quality tradeoffs as it applies to neural network architectures and practical experience making said tradeoffs

• Experience in ML-driven production systems that develops models with large-scale data, training, evaluation, and deployment
• Experience with developing  and optimizing large-scale vision, video, or multi-modal foundation models
• Familiarity with end-to-end models and their development challenges
• Agility in a fast-paced environment