Machine Learning & Data Engineer, Vehicle Modeling at 42dot in Sunnyvale, United States

Job description

• Application
• We are building next-generation vehicle modeling and data technology at 42dot by combining physics-based models, machine learning, simulation, and large-scale vehicle data.
• As a Machine Learning & Data Engineer, Vehicle Modeling, you will develop ML and data infrastructure that improves vehicle models and supports broader vehicle intelligence and autonomous driving development. You will work across vehicle telemetry, simulation, test data, fleet data, and cloud platforms to build scalable systems for model development, evaluation, and continuous improvement.
• A core focus of this role is using real-world vehicle data to identify model performance gaps and improve models through calibration, parameter estimation, machine learning, and hybrid physics-and-data approaches. You may develop ML models that complement physics-based models, estimate model parameters under different vehicle states and operating conditions, or improve predictions where physical models alone are insufficient.
• You will also help build the data and cloud infrastructure needed to ingest, clean, organize, process, and evaluate large-scale vehicle datasets, supporting modeling, simulation, vehicle intelligence, and autonomous driving workflows.
• This role sits at the intersection of machine learning, data engineering, physical system modeling, simulation, and vehicle software.

Responsibilities

• Develop machine learning and hybrid physics-data approaches to improve vehicle and component model accuracy.
• Develop methods for model calibration, parameter estimation, adaptive modeling, and data-driven model improvement across different vehicle states and operating conditions.
• Build scalable workflows for comparing model predictions with test, simulation, and real-world vehicle data and identifying opportunities for model improvement.
• Build pipelines for ingesting, cleaning, synchronizing, transforming, storing, and accessing large-scale vehicle telemetry and time-series data.
• Develop cloud-based infrastructure for data processing, model training, simulation, evaluation, and validation.
• Build tools and workflows for dataset management, model evaluation, experiment tracking, and reproducible model development.
• Support data processing, model evaluation, and analysis workflows used by vehicle intelligence

Requirements

• Develop machine learning and hybrid physics-data approaches to improve vehicle and component model accuracy.
• Develop methods for model calibration, parameter estimation, adaptive modeling, and data-driven model improvement across different vehicle states and operating conditions.
• Build scalable workflows for comparing model predictions with test, simulation, and real-world vehicle data and identifying opportunities for model improvement.
• Build pipelines for ingesting, cleaning, synchronizing, transforming, storing, and accessing large-scale vehicle telemetry and time-series data.
• Develop cloud-based infrastructure for data processing, model training, simulation, evaluation, and validation.
• Build tools and workflows for dataset management, model evaluation, experiment tracking, and reproducible model development.
• Support data processing, model evaluation, and analysis workflows used by vehicle intelligence

Skills

Required

• Machine learning
• Data engineering
• Physics-based modeling
• Simulation
• Cloud infrastructure
• Data pipeline development
• Time-series data processing