Machine Learning Engineer (Scenes)

Waymo; San Francisco (CA); Hybrid; USD 180,000 - 260,000; Full time

Benefits offered by this job

Medical, dental, and vision insurance

Hybrid work model

Onsite meals & snacks

Fitness centers & wellness programs

Paid time off & leave

Job summary

Waymo LLC is seeking a Machine Learning Engineer in DRV to bridge cutting-edge ML with real-world vehicle performance. You will own features for Scene Understanding from data to onboard launch, curate large driving data sets, and iteratively improve model calibration and robustness for new geographies.

You will design multi-task heads, build rigorous evaluations, and integrate models into the onboard stack with safe fallbacks.

Qualifications

• Hands-on experience shipping ML models to production, including training, offline evaluation, and deployment (L4: 2+ yrs; L5: 4+ yrs, or a PhD plus 2+ yrs)
• Cross-stack problems spanning data, model and systems/serving boundaries
• Strong data mining and data engineering to build large-scale batch pipelines
• Rigorous evaluation instincts: metric design, error analysis and slicing, A/B or staged rollout
• Proficiency in Python with a modern DL framework (JAX, TensorFlow, or PyTorch) and production C++
• Experience with transformer or temporal models (GRU/RNN), multi-task learning, and model calibration/uncertainty
• AV/Robotics experience, especially perception (detection, classification, tracking)
• TPU/accelerator performance work; exporting models for onboard/edge inference
• Labeling-pipeline and supervision design; autolabeling or synthetic data
• Builds internal tools (visualization, triage, experiment tracking) that accelerate the team

Responsibilities

• Bridge ML with real-world vehicle performance in validation and onboard systems
• Own ML features for Scene Understanding end to end: data → model → eval → onboard launch
• Mine and curate large-scale driving data (real and simulated) for training and evaluation
• Design, train, and iterate on multi-task model heads; improve calibration and generalization
• Build rigorous evaluation: metrics, slicing, side-by-sides, staging launches
• Integrate models into onboard stack (C++), with safe heuristics and map-contradiction handling
• Triage real driving events, diagnose root causes, propose fixes with cross-team collaboration

Skills

Data mining

Data engineering

Python (DL frameworks)

C++ production

Transformer/temporal models

Multi-task learning

Model calibration/uncertainty

Cross-stack generalist

Education

BS/MS/PhD in CS, EE, Robotics, ML or related

Tools

Beam/Flume/Spark

Job description

• As a Machine Learning Engineer in DRV, you will bridge the gap between cutting-edge machine learning and real-world vehicle performance, engineering the validation and onboard systems that ensure the autonomous vehicle reliably executes intelligent and predictable maneuvers
• Own ML features for Scene Understanding (traffic controls, signs, special regions such as RRX and flood zones, lane states) end to end: data → model → eval → onboard launch
• Mine and curate large-scale driving data (real and simulated) to find long-tail failures, build training and eval sets, and design labeling and supervision
• Design, train, and iterate on model tasks and heads in large multi-task models. Improve calibration, robustness, and generalization to new geographies
• Build rigorous evaluation: PRT metrics, slicing taxonomies, side-by-sides, and staging launches, and turn the results into launch decisions
• Integrate models into the onboard stack (C++) , combining learned outputs with safe heuristic fallbacks, Mendel-guarded rollouts, and map-contradiction handling
• Triage real driving events, find the root cause anywhere in the stack, and propose surgical or systemic fixes. Work closely with Perception, Reasoning, Mapping, and ML Infrastructure teams

Benefits

• Medical, dental, and vision insurance for employees and dependents
• Employee assistance programs focused on mental health
• Personalized workplace adjustments for diverse needs and abilities, including physical, mental, and neurodivergent considerations
• Access to mental health apps
• Onsite wellness centers
• Second medical opinion for you and your loved ones
• Counseling services
• Support programs including menopause benefit
• Medical advocacy program for transgender employees
• Competitive compensation
• Regular bonus and equity performance grant opportunities
• Generous 401(k) and regional retirement plans
• Annual cross-company compensation review and pay equity analysis
• 1-on-1 financial coaching
• Fertility and growing family assistance
• Parental leave and baby bonding leave
• Elder care and support
• Survivor income benefitBackup childcare
• Caregiver leave
• Paid time off, including vacation, bereavement, sick leave, parental leave, disability, and holidays
• Jury duty leave
• Military leave
• Hybrid work model with remote work opportunities also available
• Educational reimbursement
• Peer learning and coaching platform
• Donation matching programs
• Volunteer hours
• Employee resource groups
• Internal community groups and local culture clubs
• Inspiring spaces to work, recharge, and collaborate with fellow Waymonauts
• On-site meals and snacks
• Fitness centers, massage programs, and ergonomic support
• On-demand fitness, wellbeing, and cooking classes
• Commuter benefits

Hands-on experience shipping ML models to production, including training, offline evaluation, and deployment (L4: 2+ yrs; L5: 4+ yrs, or a PhD plus 2+ yrs)Demonstrated cross-stack generalist work: has owned problems that crossed data, model, and systems/serving boundariesBS/MS/PhD in CS, EE, Robotics, ML, or a related field, or equivalent practical experienceStrong data mining / data engineering: building large-scale batch pipelines (Beam/Flume/Spark or similar) and analytical SQL to find, slice, and curate dataRigorous evaluation instincts: metric design, error analysis and slicing, and A/B or staged rolloutProficiency in Python with a modern DL framework (JAX, TensorFlow, or PyTorch) and production C++Experience with transformer or temporal models (GRU/RNN), multi-task learning, and model calibration/uncertaintyAV/Robotics experience, especially perception (detection, classification, tracking)TPU/accelerator performance work; exporting models for onboard/edge inferenceLabeling-pipeline and supervision design; autolabeling or synthetic dataBuilds internal tools (visualization, triage, experiment tracking) that accelerate the team