Machine Learning Engineer - Spatial AI

• 11 septembre 2026
• 100%
• Durée indéterminée
• Paudex

Do you want to dive into the growing drone industry and gain rewarding experience in a dynamic scale-up environment?

At Flyability, we believe that robots should be sent into dangerous places and risky environments instead of humans. To support this conviction, we created Elios, the world's first collision-tolerant flying robot, capable of safely entering, examining, and inspecting confined spaces so that people do not have to. With more than 150 employees and 1-500 clients, Flyability is the market leader in the UAS indoor inspection industry. Joining Flyability is not just taking a new job; it is seizing the opportunity to improve the lives of millions of people and contribute to the future of robotics.

To complete our creative and dynamic team in Lausanne, we are looking for a :

Machine Learning Engineer - Spatial AI (100%)
Ideal start date: as soon as possible

Your role:

As a member of the Autonomy team, you will develop AI-based perception and spatial understanding for Flyability's inspection drones. You will combine 2D images and 3D point clouds to build robust semantic representations of complex indoor environments.

You will work at the intersection of computer vision, machine learning, and robotics, connecting information from different views and detection modalities. You will bridge the gap between research and engineering, transforming ambitious ideas into robust capabilities for real robotic systems.

What you will take on:

• Design and implement state-of-the-art AI models and algorithms for 2D/3D scene understanding
• Combine camera data and point clouds into coherent semantic spatial maps, leveraging multi-view and multimodal information
• Develop semantic understanding to support mapping, navigation, inspection planning, and natural language guided missions
• Prepare and analyze real drone datasets
• Evaluate models using relevant quantitative metrics, visualizations, and targeted experiments, and transform failure cases into model improvements
• Build reliable research and production pipelines in Python/PyTorch, from experimentation to deployment
• Collaborate with the mapping, sensor, and product teams to integrate spatial AI capabilities into real inspection systems

Your profile:

We are looking for an engineer motivated by the challenge of helping robots understand the physical world, capable of combining strong machine learning knowledge with good engineering practices.

You bring:

• More than 3 years of experience in developing machine learning or computer vision systems in academic, industrial, or robotics settings
• Deep expertise in modern semantic segmentation, particularly in 2D imaging and/or 3D point clouds, including model architectures, training strategies, data preparation, and evaluation
• Proven experience in developing production-quality computer vision systems based on semantic segmentation, instance segmentation, or object detection, from data and training to evaluation and deployment
• Strong proficiency in Python and PyTorch, with the software engineering skills necessary to transform research ideas into maintainable systems
• A good understanding of the full ML lifecycle, including evaluating model performance in new environments, monitoring degradation and emerging failure modes, and identifying improvements requiring better data, retraining, or model modifications
• Experience with real datasets, systematic error evaluation, and analysis, with a strong ability to transform failure cases into concrete model improvements
• An interest in 3D computer vision, multimodal perception, sensor fusion, or spatial AI, and in combining observations from cameras, point clouds, and multiple viewpoints
• The ability to navigate easily between research, prototyping, and production, and to transform promising ideas into robust robotic capabilities
• Proficiency in English; French is a plus

Assets:

• Experience in multi-view geometry, 3D reconstruction, SLAM, or semantic mapping
• Experience in deploying AI models on robotic or resource-constrained embedded platforms
• Experience working with robotic systems or autonomous platforms
• A strong interest in the link between semantic maps, perception, and language to enable natural language interaction with robots
• Experience in LLM fine-tuning, RAG, and evaluation, ideally applied to real or multimodal AI systems

Advantages and benefits you will love:

• Enjoy 25 days of leave per year, plus all public holidays to recharge and explore
• Additional days are granted based on your seniority with us, up to 5 days.
• Stay safe with comprehensive accident insurance covering medical care and hospitalization
• Work at your own pace with flexible hours and the possibility to telework up to 2 days per week
• Improve your well-being with discounts on gym memberships and sporting events
• Access exclusive benefits via Swibeco, our platform offering