Autonomy Engineer - Deep Learning Model Acceleration

Skydio · Defense · Zurich, Switzerland · R&D

The Autonomy Engineer - Deep Learning Model Acceleration role at Skydio focuses on building and scaling infrastructure for AI/ML efforts, specifically optimizing deep learning inference for computer vision workloads on various hardware platforms. This involves profiling models, designing MLOps workflows, improving training efficiency, implementing GPU kernels, and creating SDKs for autonomous workflows, with a strong emphasis on edge deployment and performance optimization.

What you'd actually do

  1. Develop solutions for high-performance deep learning inference for CV workloads that can deliver high throughput and low latency on different hardware platforms
  2. 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
  3. Design and implement end to end MLOps workflows for model deployment, monitoring, and re-training
  4. Utilize advanced Machine Learning knowledge to leverage training or runtime frameworks or model efficiency tools to improve system performance
  5. Create new methods for improving training efficiency

Skills

Required

  • MLOps
  • ML inference acceleration/optimization
  • edge deployment
  • DL fundamentals
  • CV fundamentals
  • image processing
  • video processing
  • ML pipelines
  • model training
  • model deployment
  • monitoring
  • ML frameworks and libraries
  • software lifecycle management
  • complex codebase navigation
  • collaboration

Nice to have

  • Vision Language Models (VLMs)
  • GPU kernels
  • custom architectures
  • SDK development

What the JD emphasized

  • ML inference acceleration/optimization
  • edge deployment
  • high-performance deep learning inference
  • low latency
  • power efficiency
  • MLOps workflows
  • model deployment
  • model efficiency tools
  • training efficiency
  • optimized inference
  • autonomous workflows
  • ML infrastructure

Other signals

  • Deep Learning Model Acceleration
  • high-performance deep learning inference
  • MLOps workflows for model deployment
  • improve system performance
  • ML inference acceleration/optimization
  • edge deployment