Robotics AI Intern - Visual Detection with Pretrained & Few-Shot Learning

Flyability

  • Paudex, Vaud
  • Stage
  • Temps-plein
  • Il y a 28 jours
  • Postuler facilement
Do you want to dive into the fast-growing industry of drones and get a rewarding experience in a dynamic start-up environment?At Flyability, we believe that robots should be sent into hazardous places and dangerous situations instead of humans. To support our belief, we created Elios, the world’s first collision-tolerant flying robot that for the first time allows remote entry to complex and indoor spaces. With more than 100 employees, Flyability is the pioneer in the UAV indoor inspection industry. Joining Flyability is not just taking on a new job, it is seizing the opportunity to improve the life of millions of people and build the future of robotics.To complete our creative and dynamic team in Lausanne, we are seeking a:Robotics AI Intern – Visual Detection with Pretrained & Few-Shot Learning (100%)
Starting date: as soon as possibleYour role:In this role you will apply pretrained and few-shot learning techniques to develop AI-based visual detection tools for robotics. You will help design and create labeled datasets, enabling users to identify objects or defects with minimal examples and generalize across large image collections. This includes experimenting with model behavior, building intuitive labeling workflows, and supporting integration into real-world inspection systems.What you will own:
  • Design, train, and refine models for detecting visual patterns such as cracks, rust, or other anomalies
  • Support dataset creation and labeling strategy to ensure high-quality training data for supervised and few-shot learning
  • Integrate models into Flyability’s software stack and validate them in simulation or real-world conditions
  • Define evaluation metrics and assess model performance for reliability, accuracy, and efficiency in deployment scenarios
RequirementsYour profile:
  • Experience with modern AI frameworks such as PyTorch or TensorFlow
  • Solid understanding of machine learning workflows: data preprocessing, model training, evaluation, and deployment
  • Proficient in Python, with good software engineering practices
  • Analytical mindset with a practical, hands-on approach to testing AI systems in robotic or embedded environments
  • Familiarity with visual defect detection methods is a plus
  • Fluent in English; proficiency in additional languages is a plus
Flyability is a young Swiss company that values independent thinking combined with a collaborative spirit. Every day, you will have the opportunity to share your ideas and contribute to solving problems. We all work together, and each voice is important to move forward.Ready to join?We know the confidence gap and impostor syndrome can get in the way of meeting spectacular candidates, so please don't hesitate to apply —regardless of your past experience or resume, we'd love to hear from you.

Flyability