Sr. Staff Systems Engineer Autonomy

Rivian•Palo Alto, CA

About The Position

We are seeking an expert AV data strategist to architect the data engine and collection frameworks that power our next-generation perception and end-to-end autonomous driving models. Sitting at the intersection of systems engineering, machine learning infrastructure, and vehicle operations, you will design the system-level strategies for how we identify, capture, and utilize fleet data. Your work will ensure our models are trained and evaluated on highly relevant, diverse, and safe datasets, prioritizing high-quality continuous driving sequences while balancing strict vehicle edge constraints.

Requirements

Advanced degree (Master’s or Ph.D.) in Systems Engineering, Computer Science, Robotics, Machine Learning, Data science or a related technical field .
10+ years (Bachelor’s)/8+ years (Master’s) of experience in systems engineering, data strategy, or MLOps, preferably carrying out listed responsibilities in the Autonomous driving or robotics industry.
Understanding of autonomy data requirements for perception models, end-to-end models, imitation learning, and sensor-to-trajectory model training lifecycles.
Demonstrated ability to build technical frameworks from the ground up and drive consensus among teams such as ML software, data and cloud infrastructure and vehicle operations.
Medium to Strong programming skills in Python and one or more query language (e.g., SQL, PL/SQL, DDL, MDX, HiveQL, SparkSQL, Scala)
Knowledge of privacy engineering, data privacy, security risks, and controls
Excellent team player with strong communication and presentation skills.

Responsibilities

Define and document comprehensive data requirements to support diverse training, development and evaluation use cases across the autonomy stack.
Build and manage a decision-making framework with cross-functional stakeholders. Use this framework to determine data availability, identify gaps between required vs. available data, and prioritize collection efforts of desired driving behaviors, trajectory profiles or scenes.
Driven by the gap analysis, devise strategies to capture required data from the fleet. Ensure the data meets required recall, precision and diversity requirements while operating within the constraints of on-vehicle data logging, privacy, and upload bandwidth.
Collaborate with Autonomy ML teams to systematically identify model failure modes and define requirements for targeted data mining campaigns to resolve them.
Define strategies and standards for data slicing tailored to training, development and evaluation of autonomy perception, planning and end-to-end models. Coordinate the deployment of tagging with data and cloud teams.
Curate diverse, high fidelity datasets that capture targeted ODD scenes and human driving demonstrations, systematically filtering out sub-optimal behaviors.
Review and provide strategic inputs on perception taxonomy requirements—such as defining object and scene classifications, attributes etc.—to meet the demands of different autonomy features on the target vehicle platform or target customer market.
Define system metrics to evaluate the health, diversity, and potential bias of driving datasets, ensuring they accurately represent our Operational Design Domain (ODD) and comply with safety and verification standards.