Autonomy Engineer - Deep Learning

As a Deep Learning Engineer at Skydio, you will train and deploy optimized models for real-time autonomous flight, solving challenges like optical flow, depth estimation, object detection, and mapping. You will leverage real-world and synthetic data, refine models for embedded hardware, and develop evaluation benchmarks to advance intelligent aerial robots.

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

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