Classical Algorithm Engineer for Camera-LiDAR based Multimodal Perception (Automated Driving)

At Qualcomm, we are transforming the automotive industry with our Snapdragon Digital Chassis and building the next generation software defined vehicle (SDV). Snapdragon Ride is an integral pillar of our Snapdragon Digital Chassis, and since its launch it has gained momentum with a growing number of global automakers and Tier1 suppliers.  Snapdragon Ride aims to address the complexity of autonomous driving and ADAS by leveraging its high-performance, power-efficient SoC, industry-leading artificial intelligence (AI) technologies and pioneering vision and drive policy stack to deliver a comprehensive, cost and energy efficient systems solution.  

Enabling safe, comfortable, and affordable autonomous driving includes solving some of the most demanding and challenging technological problems. From centimeter-level localization to multimodal sensor perception, sensor fusion, behavior prediction, maneuver planning, and trajectory planning and control, each one of these functions introduces its own unique challenges to solve, verify, test, and deploy on the road. 

What you'll do?

We are ramping up the development of our fifth-generation vision perception and driver policy platform. The platform has already had commercial success with a major German vehicle manufacturer sourcing it for upcoming luxury vehicles. The platform will include solutions for the next generation advanced driver assist systems (ADAS) and autonomous driving (AD) with the goal of being the global market leader.

Deep learning is becoming ever more important for the drive stack. This requires systematically engineering the labeled data to unlock the full power of an AI system. Areas include data preparation, automated file selection (sampling, active learning), auto-labeling, automated review and quality assurance, data set quality measurement, and data set analysis (e.g., core set and edge case extraction). These areas require strong expertise in classical algorithm development as well, ranging from geometric computer vision, 3-D point cloud processing, to classical filter and estimation theory. For instance, data preparation requires cross-sensor calibration and accurate ego-pose estimation in challenging GPS environments. To reach high yields in auto-labeling, conventional estimation and filter theory comes in handy. Similarly, automated review benefits from sanity checks based on classical signal processing. Teams working on this are in India, Sweden, Romania, Germany, and the US.

You will work in an Agile environment and actively participate in Scrum practices like standups, planning, retrospective, demos, continuous interactions with customer for feedback.

We work in cross functional teams. While each team member contributes with their own skills and experience, the team cooperates to perform the different steps in development. The teams are responsible for all steps in development, including system work, implementation, and verification.

Minimum Qualifications:

• Excellent communication skills
• Proficiency in Python
• Experience with multi-modal perception sensors used in robotics and automotive, such as camera, lidar, radar
• Experience with geometric computer vision, 3-D point cloud processing, image processing, and relevant software packages

Educational Criteria:

• Bachelor's degree in Engineering, Information Systems, Computer Science, or related field and 3 - 7 years of algorithm development related to automotive sensors or related work experience.

​OR

• Master's degree in Engineering, Information Systems, Computer Science, or related field and 2 - 5 years of algorithm development related to automotive sensors or related work experience.

OR

• PhD in Engineering, Information Systems, Computer Science, or related field and 1 - 4 years of algorithm development related to automotive sensors or related work experience.