Autonomy Engineer - Deep Learning

Skydio•San Mateo, CA

About The Position

Skydio is the leading US drone company and the world leader in autonomous flight, the key technology for the future of drones and aerial mobility. The Skydio team combines deep expertise in artificial intelligence, best-in-class hardware and software product development, operational excellence, and customer obsession to empower a broader, more diverse audience of drone users. From utility inspectors to first responders, soldiers in battlefield scenarios and beyond. About the role: Learning a semantic and geometric understanding of the world from visual data is the core of our autonomy system. We are pushing the boundaries of what is possible with real-time deep networks to accelerate progress in intelligent aerial robots that can autonomously navigate in unknown environments and deliver operational value to users. If you are excited about real world applications of deep learning and solving difficult problems in computer vision and autonomy, we would love to hear from you. As a Deep Learning Engineer, you will be responsible for training and deploying optimized models to our products for solving challenging problems such as optical flow estimation, stereo depth estimation, object detection, segmentation and tracking, visual place recognition, localization and mapping, few-shot learning, occupancy networks, automated path planning etc.

Requirements

M.S. or Ph.D. in computer science, electrical engineering or related discipline
Demonstrated hands-on experience designing, training and deploying deep learning models
Ability to deliver high quality, well-architected code (Python/PyTorch and preferably, C++)
Leverage state-of-the-art academic papers and literature for fast iteration
Ability to thrive in a fast paced, collaborative and highly technical team environment
Comfortable navigating and delivering within a complex codebase
Strong communication skills

Responsibilities

Design, implement, and deploy computer vision and multimodal deep learning models for Skydio’s autonomy system
Leverage massive amounts of real world video and other sensor data for data mining, curation, labeling, training and evaluation
Leverage large scale and diverse synthetic data to power deep learning algorithms
Leverage state-of-the-art foundation models for knowledge distillation and label efficient learning
Refine and optimize models for low-latency on embedded hardware
Develop evaluation benchmarks and metrics to quantify the performance of autonomous systems
Be a generalist helping out on all aspects of the software when needed