Senior Planning & Control Engineer, Validation & Evaluation

AI overview

Lead validation algorithms and build scalable evaluation pipelines for autonomous trucking systems, ensuring performance measurement and algorithm improvements before deployment.

Company Introduction

Bot Auto is revolutionizing the transportation industry by developing fully autonomous Class 8 commercial motor vehicles. The proprietary technology that fuels our autonomous driving system represents our core intellectual property, requiring best-in-class security measures and leadership.

Role Overview

We are seeking a Senior Planning & Control Engineer to lead validation algorithms and evaluation pipelines for our autonomous trucking system. This role focuses on defining metrics, building scalable validation infrastructure, and deeply analyzing planning and control behavior across simulation and real-world data.
You will own how planning and control performance is measured, trusted, and improved prior to deployment.

Responsibilities

Design and implement validation algorithms and metrics for planning and control performance (safety, comfort, efficiency, compliance).

Build and maintain scalable evaluation pipelines for offline and closed-loop testing.
Analyze failures and regressions, identify root causes, and drive algorithm improvements.
Partner closely with planning, control, simulation, and safety teams to validate new capabilities before release.
Provide technical leadership on validation methodology and best practices.

Qualifications

BS/MS in CS, Robotics, EE, ME, or related field.
Strong C++ and Python skills.
Solid understanding of motion planning, trajectory generation, and feedback control.

Experience validating autonomous systems, robotics, or other safety-critical software.
Ability to reason about system-level behavior using large-scale real-world data.

Nice to Have

Experience with autonomous vehicles or trucking systems.

Background in vehicle dynamics, control theory, or optimization.
Experience designing metrics that distinguish real regressions from noise.