System Software Engineer, Calibration - Autonomous Vehicles

NVIDIA•Santa Clara, CA

2d•$152,000 - $287,500

About The Position

NVIDIA is seeking a Software Engineer to support calibration for autonomous vehicles. The role involves developing and validating calibration and egomotion algorithms on vehicles, maintaining and productizing existing calibration approaches, triaging support issues, and monitoring calibration performance across a vehicle fleet. The engineer will work with NVIDIA’s OEM partners to bring up existing and new calibration-related features on prototype and pilot production vehicles. The position focuses on sensor calibration for ADAS using classical and deep learning methods, evaluating algorithms with real and synthetic data, and developing software architecture and frameworks for real-world performance. Work spans camera, LIDAR, radar, IMU, GPS, odometry, and other sensor modalities. The engineer will develop efficient C++ product code using CUDA, meet quality and safety standards such as MISRA and AUTOSAR, build fleet-monitoring tools, and perform in-vehicle testing, troubleshooting, data analysis, and drive missions.

Requirements

PhD with at least 1 year, MS with at least 3 years, or BS (or equivalent experience) with at least 5 years of relevant experience in Computer Science, Computer Engineering, or a related technical field.
Excellent C++ and Python programming skills.
General knowledge of fundamental algorithms in robotics, controls/estimation, and 3D computer vision.
Strong knowledge of programming and debugging techniques, especially for automotive or robotics systems.
Strong communication and analytical skills, including the ability to contribute critical and constructive design and code reviews.
Comfort working with local and remote Linux machines, Git, and build systems.
Self-motivation and ability to work as a teammate.

Nice To Haves

Experience with data-parallel and/or CUDA programming.
Experience with performance analysis, optimization, and benchmarking.
Background with automotive systems, particularly ADAS applications.
Deep experience with Bazel, Docker, VSCode plugins, and code-analysis or quality-of-life tools.
Proven track record on calibration-related projects, such as developing new calibration algorithms.

Responsibilities

Develop new approaches and improve existing sensor calibration algorithms for ADAS using classical and deep learning methods.
Use real and synthetic data to evaluate and improve the algorithmic and computational performance of sensor calibration.
Develop and optimize software architecture and frameworks to meet real-world performance and internal and external customer requirements.
Work with camera, LIDAR, radar, IMU, GPS, odometry, and other sensor modalities.
Develop unit tests and feature documentation, evaluate quality, and propose improvements and corrective actions.
Develop efficient C++ product code using the algorithmic parallelism available through GPGPU programming with CUDA.
Develop production code to quality and safety standards such as MISRA and AUTOSAR.
Develop and maintain fleet-monitoring tools supporting calibration across a large vehicle fleet.
Perform in-vehicle testing and troubleshooting, mine and analyze data, and complete drive missions.
Adopt and improve calibration algorithms for existing and new vehicle variants.
Support calibration and egomotion algorithm development and validation on vehicles, productize existing approaches, triage support issues, and monitor calibration performance.
Work with OEM partners to bring up calibration-related features on prototype and pilot production vehicles.