Machine Learning Engineer, Driver Refinement & Validation, Perception
About this role
Engineers who thrive on tackling complex real-world challenges through large-scale data and machine learning will find a strong fit within this autonomous driving team. Waymo builds autonomous driving technology aimed at improving mobility and traffic safety, powering a fully autonomous ride-hail service across multiple states.
This role sits within the Perception team focusing on driver refinement and validation. Practitioners will own end-to-end driving behavior for various on-road problem clusters, collaborating closely with upstream and downstream teams to build and integrate machine learning models. Responsibilities include scaling training recipes, analyzing real-world behavior, monitoring production systems, and developing evaluation metrics using vast amounts of driving data.
What you will do
- Own tasks within the machine learning driver, take responsibility for task performance, and create methods to scale and improve those tasks.
- Analyze the behavior of machine learning systems in real-world applications to identify issues, determine root causes, and advise on or develop short- and long-term solutions.
- Develop distributed fine-tuning methods and recipes that allow multiple developers to simultaneously improve models while avoiding regressions against production systems.
- Monitor machine learning systems in production, build automated detection mechanisms for issues and regressions, and create AI-aided analysis and debugging tools.
- Develop and maintain model evaluation recipes and metrics to measure and improve the performance of both pre-trained and fine-tuned models.
What you need
- Hold a Bachelor's degree in Computer Science or a similar discipline, or possess an equivalent amount of deep learning experience.
- Bring at least three years of professional experience working in machine learning and/or computer vision.
- Demonstrate programming proficiency in Python or C++.
- Show hands-on experience using machine learning frameworks such as PyTorch or JAX.
Nice to have
- MS or PhD Degree in Machine Learning, Robotics, Computer Science or a similar discipline
- Publications at top-tier conferences like CVPR, ICCV, ECCV, ICLR, ICML, ICRA, IROS, RSS, NeurIPS, AAAI, IJCV, PAMI
Benefits
- Discretionary annual bonus program
- Equity incentive plan
- Generous company benefits program
Skills and tech stack
Questions candidates ask
What is the work location policy for this role?
This is a hybrid role based in Mountain View, California or San Francisco, California. The expected base salary range applies across US locations.
What is the compensation package for this position?
The expected base salary range is $175,000 to $215,000 USD. Employees are also eligible to participate in a discretionary annual bonus program, equity incentive plan, and company benefits program.
What tools and technologies will I be working with?
The work involves using Python or C++ alongside machine learning frameworks such as PyTorch or JAX. Engineers will interact with millions of miles of driving data from a diverse set of sensors.
Who will I report to?
In this hybrid role, you will report directly to a Technical Lead Manager. You will collaborate with upstream and downstream teams to develop and integrate models.