Back to jobs
Logo of Skydio
Skydio
Actively hiring

Autonomy Engineer - Deep Learning Model Acceleration

Workplace
Hybrid
Commitment
Full-time
Posted
Location
Zurich, Switzerland

As a deep learning model acceleration engineer at Skydio, you will build and scale infrastructure to support deep learning and AI efforts, working at the nexus of autonomy, embedded, and cloud teams to deliver new capabilities and empower the deep learning team.

Responsibilities

  • Develop solutions for high-performance deep learning inference for CV workloads that can deliver high throughput and low latency on different hardware platforms
  • Profile CV and Vision Language Models (VLMs) to analyze performance, identify bottlenecks and acceleration/optimization opportunities and improve power efficiency of deep learning inference workloads
  • Design and implement end to end MLOps workflows for model deployment, monitoring, and re-training
  • Utilize advanced Machine Learning knowledge to leverage training or runtime frameworks or model efficiency tools to improve system performance
  • Create new methods for improving training efficiency
  • Implement GPU kernels for custom architectures and optimized inference
  • Design and implement SDKs that allow customers/external developers to create autonomous workflows using Machine Learning (ML)
  • Leverage your expertise and best-practices to uphold and improve Skydio’s engineering standards

Requirements

  • Demonstrated hands-on experience with MLOps, ML inference acceleration/optimization, and edge deployment
  • Strong knowledge of DL fundamentals, techniques, and state-of-the-art DL models/architectures
  • Strong fundamentals in CV, image processing, and video processing
  • Demonstrated hands-on experience building and managing ML pipelines for solving vision or vision language tasks including data preparation, model training, model deployment, and monitoring
  • Experience and understanding of security and compliance requirements in ML infrastructure
  • Experience with ML frameworks and libraries
  • You have demonstrated ability to take a concept and systematically drive it through the software lifecycle: architecture, development, testing, and deployment, and monitoring
  • You are comfortable navigating and delivering within a complex codebase
  • Strong communication skills and the ability to collaborate effectively at all levels of technical depth