Senior Autonomy Engineer - Deep Learning

Skydio Skydio · Defense · Zurich, Switzerland · R&D

Senior Autonomy Engineer focused on designing, implementing, and optimizing deep learning models for real-time object detection, tracking, segmentation, and optical flow estimation on embedded drone hardware. The role involves leveraging state-of-the-art methods, curating synthetic and real-world data, and refining models for low-latency performance, with a strong emphasis on software engineering and deploying deep neural networks.

What you'd actually do

  1. Design and implement deep learning solutions that solve detection, tracking, segmentation, and optical flow estimation tasks in real-time on Skydio drones
  2. Leverage state-of-the-art methods in unsupervised learning, few shot learning, and foundational models for data efficient ML
  3. Curate and enhance synthetic data that powers our deep learning algorithms along with massive amounts of structured video data
  4. Refine and optimize models for low-latency on embedded hardware
  5. Characterize and quantify the performance of the vision systems

Skills

Required

  • Demonstrated hands-on experience creating and deploying deep learning models
  • Experience curating synthetic and real-world image datasets
  • Solid software engineering foundation and commitment to writing clean, well-architected code (in Python or C++, preferably both)
  • Real experience prototyping, training, optimizing, and deploying deep neural networks
  • Ability to read and contextualize scientific papers and literature in computer vision

Nice to have

  • Python
  • C++

What the JD emphasized

  • real-time
  • low-latency on embedded hardware
  • deep learning solutions
  • detection, tracking, segmentation, and optical flow estimation
  • unsupervised learning, few shot learning, and foundational models
  • synthetic data
  • structured video data
  • optimize models
  • embedded hardware
  • performance of the vision systems
  • deep neural networks

Other signals

  • real-time deep networks
  • intelligent mobile robots
  • object detection and tracking
  • motion prediction
  • flow estimation
  • total scene understanding
  • massive amounts of structured video data
  • low-latency on embedded hardware