Autonomy Engineer - Deep Learning Model Acceleration

Skydio
Zurich
Workplace: HybridFull timeFunction: Data Science & Machine LearningSkills: ["MLOps","Inference acceleration","Edge deployment","Python","PyTorch","TensorFlow","CUDA","GPU","GPU kernels","Model deployment","Monitoring"]

Own the performance of deep learning inference for computer vision workloads on diverse hardware. Build scalable MLOps for deployment, monitoring, and retraining; profile CV and Vision Language Models to optimize speed and power efficiency; create GPU kernels and SDKs to enable external developers; work across autonomy, embedded, and cloud teams to raise engineering standards.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Skydio
Skydio
3 months ago

Autonomy Engineer - Deep Learning Model Acceleration

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 2 hours agoStatus: Live
Reposted: similar role first listed 8 months ago

Job Summary

Own the performance of deep learning inference for computer vision workloads on diverse hardware. Build scalable MLOps for deployment, monitoring, and retraining; profile CV and Vision Language Models to optimize speed and power efficiency; create GPU kernels and SDKs to enable external developers; work across autonomy, embedded, and cloud teams to raise engineering standards.
Location: Zurich
Workplace: Hybrid
Employment Type: Full time
Job Function: Data Science & Machine Learning

Key Responsibilities

  • •Develop high-performance deep learning inference solutions for CV workloads with high throughput and low latency across hardware platforms.
  • •Profile CV and Vision Language Models to identify bottlenecks and opportunities for acceleration/optimization and improve power efficiency.
  • •Design and implement end-to-end MLOps workflows for model deployment, monitoring, and re-training.
  • •Leverage training/runtime frameworks and model efficiency tools to improve system performance.
  • •Create new methods to improve training efficiency and implement GPU kernels for custom architectures and optimized inference.

Key Requirements

  • •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.
  • •Experience building and managing ML pipelines for vision/vision-language tasks including data prep, model training, deployment, and monitoring.
  • •Experience with security and compliance requirements in ML infrastructure.
Skills:MLOpsInference accelerationEdge deploymentPythonPyTorchTensorFlowCUDAGPUGPU kernelsModel deploymentMonitoring
Tech Stack:CUDAPyTorchTensorFlowGPUMLOpsEdge computing

Company Brief

Skydio
Designs and manufactures autonomous consumer and enterprise drones using AI-powered vision and navigation systems for inspection, mapping, public safety, and industrial applications. Focuses on rugged, fully autonomous flight and end-to-end drone solutions.
Industry: Drones & Aerial Logistics
Company Size: Large (251 to 1,000 employees)
Growth: Scaleup
Valuation: Unicorn (USD 1B+)
Funding: Series D
Headquarters: San Mateo, United States
Founded: 2014
WebsiteLinkedIn