Autonomy Engineer - Deep Learning Model Acceleration
At a glance
Mid-level Machine Learning Engineering role at Skydio. Zurich · full-time.
Pay not stated Machine Learning Engineering salary
aimlroles summary, based on the employer's posting.
What you'll do
- Build fast, low-latency inference for computer vision models across different hardware platforms
- Profile vision and vision-language models to find bottlenecks, improve speed and reduce power use
- Create workflows for deploying, monitoring and retraining models, and develop methods to make training more efficient
- Write GPU kernels and inference optimizations, then build SDKs for machine-learning-based autonomous workflows
- Work across autonomy, embedded and cloud teams to deliver capabilities and maintain engineering standards
What you bring
- Hands-on work accelerating and optimizing ML inference, deploying models at the edge and building MLOps systems
- Strong grounding in deep learning, computer vision, image processing and video processing
- Experience building and operating pipelines for vision or vision-language tasks, from data preparation through deployment and monitoring
- Knowledge of ML frameworks and libraries, plus security and compliance needs for ML infrastructure
Who this fits
This mid-level engineering role suits someone who can take ML concepts through architecture, development, testing and deployment, and work comfortably in a complex codebase. The position is based in Zurich and follows a hybrid arrangement.
From the employer
Skydio is the leading US drone company and the world leader in autonomous flight, the key technology for the future of drones and aerial mobility. The Skydio team combines deep expertise in artificial intelligence, best-in-class hardware and software product development, operational excellence, and customer obsession to empower a broader, more diverse audience of drone users, from utility inspectors to first responders, soldiers in battlefield scenarios, and beyond.
About the role:
Learning a semantic and geometric understanding of the world from visual data is the core of our autonomy system. We are pushing the boundaries of what is possible with real-time deep networks to accelerate progress in intelligent mobile robots. If you are excited about leveraging massive amounts of structured video data to solve problems in Computer Vision (CV) such as object detection and tracking, optical flow estimation and segmentation, we would love to hear from you.
As a deep learning model acceleration engineer, you will be responsible for building and scaling the infrastructure that supports Skydio’s Deep Learning (DL) and AI efforts. You will be working at the nexus of Skydio’s autonomy, embedded and cloud teams to deliver new capabilities and empower the deep learning team.
How you’ll make an impact:
Develop solutions for high-performance deep learning inference for CV workloads that can deliver high throughput and low latency on different hardware platforms
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
Design and implement end to end MLOps workflows for model deployment, monitoring, and re-training
Utilize advanced Machine Learning knowledge to leverage training or runtime frameworks or model efficiency tools to improve system performance
Create new methods for improving training efficiency
Implement GPU kernels for custom architectures and optimized inference
Design and implement SDKs that allow customers/external developers to create autonomous workflows using Machine Learning (ML)
Leverage your expertise and best-practices to uphold and improve Skydio’s engineering standards
What makes you a good fit:
Demonstrated 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
Demonstrated hands-on experience building and managing ML pipelines for solving vision or vision language tasks including data preparation, model training, model deployment, and monitoring
Experience and understanding of security and compliance requirements in ML infrastructure
Experience with ML frameworks and libraries
You have demonstrated ability to take a concept and systematically drive it through the software lifecycle: architecture, development, testing, and deployment, and monitoring
You are comfortable navigating and delivering within a complex codebase
Strong communication skills and the ability to collaborate effectively at all levels of technical depth
At Skydio we believe that diversity drives innovation. We have created a multidisciplinary environment that embraces the power of diverse perspectives to create elegant solutions for complex problems. We are committed to growing our network of people, programs, and resources to nurture an inclusive culture.
Qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, protected veteran status, or other characteristics protected by federal, state or local anti-discrimination laws.
For positions located in the United States of America, Skydio, Inc. uses E-Verify to confirm employment eligibility. To learn more about E-Verify, including your rights and responsibilities, please visit https://www.e-verify.gov/