Responsibilities
- Develop high-performance, low-latency deep learning inference solutions for computer vision workloads across different hardware platforms.
- Profile vision and vision-language models to identify performance bottlenecks and optimize acceleration and power efficiency.
- Design and implement end-to-end MLOps workflows for model deployment, monitoring, and retraining.
- Use machine learning knowledge, training and runtime frameworks, and model-efficiency tools to improve system performance.
- Create methods to improve training efficiency.
- Implement GPU kernels for custom architectures and optimized inference.
- Design and implement SDKs that enable customers and external developers to create machine-learning-based autonomous workflows.
- Improve engineering standards and collaborate across autonomy, embedded, and cloud teams.
Requirements
- Hands-on experience with MLOps, ML inference acceleration and optimization, and edge deployment.
- Strong knowledge of deep learning fundamentals, techniques, and current deep learning model architectures.
- Strong fundamentals in computer vision, image processing, and video processing.
- Hands-on experience building and managing ML pipelines for vision or vision-language tasks, including data preparation, model training, deployment, and monitoring.
- Understanding of security and compliance requirements in ML infrastructure.
- Experience with machine learning frameworks and libraries.
- Ability to drive concepts through architecture, development, testing, deployment, and monitoring across the software lifecycle.
- Ability to navigate and deliver within a complex codebase.
- Strong communication and collaboration skills across varying levels of technical depth.
Categories
About Skydio
Skydio is the leading U.S.-based drone manufacturer and the world leader in autonomous flight technology. We leverage breakthrough artificial intelligence to create flying robots that are easier to operate, safer to fly, and more capable in complex environments. Our systems are trusted by more than 3,800 agencies and organizations across the U.S. military, public safety, and critical infrastructure sectors. Skydio Drone as First Responder (DFR) programs now operate in 42 states, and more than 16M Americans live within the response zone of a DFR Dock. In total, Skydio supports more than 1,200 public safety agencies – double the number from a year ago. More than 250 utilities rely on Skydio for inspection programs that improve reliability and worker safety. In national security, they are supporting mission-critical operations both on the battlefield and across military installations, keeping our nation and our allies secure. Founded in 2014, Skydio designs, assembles, and supports its products in the U.S., with headquarters in San Mateo, CA, and manufacturing facilities in Hayward, CA. We are the largest drone manufacturer in the U.S. and have shipped more than 60,000 flying robots. The company is backed by top investors and strategic partners, including Andreessen Horowitz, Linse Capital, N47, IVP, Playground, and NVIDIA.