Algorithm Developer - Vision Algorithms

Описание

Our Vision Localization group is responsible for accurately localizing the vehicle on a high-definition 3D map with centimeter-level precision using surround camera systems to enable autonomous driving. Our work combines advanced geometric reasoning, scene understanding, and large-scale mapping to solve one of the core challenges of autonomous vehicles in complex real-world environments. The role involves developing algorithmic and deep learning solutions that integrate mathematical optimization, computer vision, and 3D geometry.

Responsibilities

• Develop state-of-the-art localization algorithms for autonomous driving using multi-camera surround vision systems
• Design and implement deep learning models based on Transformers, Graph Neural Networks, and Convolutional Neural Networks
• Solve challenging problems involving 3D geometry, scene understanding, object matching, and spatial reasoning
• Combine learning-based methods with classical optimization and geometric algorithms
• Own the entire lifecycle from prototyping to deployment
• Analyze real-world driving data and improve system robustness under diverse environmental and visibility conditions
• Drive innovative solutions for high-precision localization at production scale

Requirements

• 2+ years of practical experience developing computer vision or machine learning solutions using Python and frameworks such as PyTorch or TensorFlow
• B.Sc. or M.Sc. in Computer Science, Electrical Engineering, or a related field, with strong academic performance
• Solid foundation in algorithms, data structures, and computer vision/deep learning fundamentals
• Strong analytical skills, a sense of ownership, and the ability to work collaboratively