Autonomy Engineer - Deep Learning Infrastructure

About the role

Skydio is building the world’s most advanced autonomous flight system. As an Autonomy Engineer focused on Deep Learning Infrastructure, you will bridge the autonomy, embedded, and cloud teams to create scalable platforms that enable real‑time computer‑vision workloads on a variety of hardware.

Key responsibilities

• Develop high‑performance deep‑learning inference solutions for computer‑vision tasks that deliver low latency and high throughput across diverse hardware platforms.
• Profile vision and vision‑language models, identify bottlenecks, and implement optimizations to improve power efficiency.
• Design end‑to‑end MLOps pipelines for model deployment, monitoring, and re‑training.
• Create custom GPU kernels and SDKs that allow external developers to build autonomous workflows.

Required profile

• Hands‑on experience with MLOps, ML inference acceleration, and edge deployment.
• Strong knowledge of deep‑learning fundamentals, state‑of‑the‑art architectures, and computer‑vision techniques.
• Proven ability to build and manage ML pipelines for vision or vision‑language tasks, including data preparation, training, deployment, and monitoring.
• Understanding of security and compliance requirements for ML infrastructure.

Required skills

• MLOps
• ML inference acceleration/optimization
• Edge deployment
• Deep‑learning frameworks (e.g., TensorFlow, PyTorch)
• Computer‑vision and video processing
• GPU kernel development
• SDK design
• Security and compliance for ML systems