Senior/Staff ML Validation Data Scientist - Perception
Software Engineering, Data Science
Foster City, CA, USA
Posted on Tuesday, October 3, 2023
You will be part of a team building state-of-the-art AI solutions for the Zoox autonomous driving Perception stack. As a member of the Perception team, you will be part of the “eyes and ears” of the Zoox autonomous driving stack, deploying state-of-the-art AI solutions to ensure safe and effective driving. In this role you will be responsible for designing and building systems to validate models on large (PBs) multimodal data. Your work will have a broad impact on shipping high performance ML models by ensuring we have comprehensive and robust evaluation pipelines to ensure safe and effective driving behavior. Think you have what it takes to build the best machine learning systems on this planet? Come join us!
- Develop and evangelize our strategy for data development and model evaluation metrics to ensure safe and effective autonomous driving, including defining objective success criteria for ML model deployment
- Analyze and interpret validation outcomes to provide recommendations to improve the performance of the ML models.
- Support data-centric AI by:
- Building a framework for measuring, reporting and iterating on label quality
- Define data labeling strategies to evaluate PCP performance for upcoming milestones
- Exploring and visualizing data to identify data distribution impact to ML models performance when deploying them in the real world
- Define key performance metrics that will help Perception engineers to directly measure the impact of the new features they are developing on the end-to-end driving behavior.
- Stay up-to-date with the latest developments in machine learning validation techniques and best practices for perception in autonomous vehicles.
- Bachelor's, Master's or PhD in CS, statistics, mathematics or relevant fields
- Background in Bayesian statistics, parametric and non-parametric statistics
- Experience designing and building evaluation system for classical and deep-learning models, including linking standard model metrics to end-to-end system behavior and key business metrics
- Experience building and presenting summary metrics to key stakeholders
- Strong understanding of statistical analysis, experimental design, and hypothesis testing, including parametrics & non-parametric testing
- Advanced knowledge of data visualization techniques
- Experience handling big data, including exposure to distributed data and/or compute, e.g. Hadoop, Spark, Hive, MapReduce, Databricks
- Experience adhering to software best practices, e.g. unit testing, DRY, abstraction, modularity, clean interfaces
- Fluent with Python-based data and statistics frameworks, e.g. numpy, scipy, pandas, statsmodels and data visualization tools, e.g. Matplotlib, Plotly
- Experience with data query languages and common databases, e.g. SQL, NoSQL, Databases
- Experience building or evaluating ML models that operate on raw sensor data (detection, classification, tracking)
- Experience with ethical AI validation
- Experience incorporating ML validation into MLOps frameworks and automation
- Experience using and/or building RESTful APIs
- Experience with dashboarding or front-end tools, e.g. Looker, Tableau, Dash, Streamlit, ReDash
There are three major components to compensation for this position: salary, Amazon Restricted Stock Units (RSUs), and Zoox Stock Appreciation Rights. The salary will range from $211,000-$300,000. A sign-on bonus may be part of a compensation package. Compensation will vary based on geographic location, job-related knowledge, skills, and experience.
Zoox also offers a comprehensive package of benefits including paid time off (e.g. sick leave, vacation, bereavement), unpaid time off, Zoox Stock Appreciation Rights, Amazon RSUs, health insurance, long-term care insurance, long-term and short-term disability insurance, and life insurance.
Zoox is developing the first ground-up, fully autonomous vehicle fleet and the supporting ecosystem required to bring this technology to market. Sitting at the intersection of robotics, machine learning, and design, Zoox aims to provide the next generation of mobility-as-a-service in urban environments. We’re looking for top talent that shares our passion and wants to be part of a fast-moving and highly execution-oriented team.
A Final Note:
You do not need to match every listed expectation to apply for this position. Here at Zoox, we know that diverse perspectives foster the innovation we need to be successful, and we are committed to building a team that encompasses a variety of backgrounds, experiences, and skills.