Autonomy Engineer - Deep Learning Infrastructure

Skydio · Defense · San Mateo, CA +1 · R&D

This role focuses on building and scaling the deep learning infrastructure for autonomous flight systems, specifically optimizing inference for computer vision workloads, managing MLOps pipelines, and implementing GPU kernels for custom architectures. It involves working with training or runtime frameworks and model efficiency tools to improve system performance and power efficiency.

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 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 optimization
  • edge deployment
  • DL fundamentals
  • state-of-the-art DL models/architectures
  • CV
  • image processing
  • video processing
  • ML pipelines
  • model training
  • model deployment
  • monitoring
  • security and compliance requirements in ML infrastructure
  • ML frameworks and libraries
  • software lifecycle (architecture, development, testing, deployment, monitoring)
  • complex codebase navigation
  • communication skills
  • collaboration skills

Nice to have

  • GPU kernels for custom architectures
  • SDK development for autonomous workflows

What the JD emphasized

  • ML inference optimization
  • edge deployment
  • ML pipelines
  • security and compliance requirements in ML infrastructure

Other signals

  • building and scaling the infrastructure that supports Skydio’s DL and AI efforts
  • high-performance deep learning inference for CV workloads
  • MLOps workflows for model deployment, monitoring and re-training
  • implementing GPU kernels for custom architectures and optimized inference