Expert Machine Learning Perception Engineer – Self-Driving

VINFAST is a pioneering electric vehicle (EV) company committed to revolutionizing the automotive industry with sustainable and innovative mobility solutions. As a leading player in the EV market, VinFast is dedicated to delivering high-quality, cutting-edge electric vehicles that redefine the driving experience. Our team consists of passionate professionals driven by a shared vision of creating a greener and more sustainable future through innovation, technology, and excellence. 

• Develop, prototype, and optimize algorithms for 3D object and occupancy detection, multi-object tracking, semantic segmentation, and 3D scene understanding using multi-sensor data (camera, LiDAR, radar, etc.) 
  

• Design and adapt foundation models for self-driving perception, enabling scalable, generalizable representations across tasks and sensor modalities 
  

• Build and improve multi-sensor fusion pipelines to enhance robustness under diverse and challenging driving scenarios 
  

• Research, adapt, and implement state-of-the-art methods in machine learning and computer vision (e.g. BEV perception, occupancy networks, multimodal fusion, end-to-end models) 
  

• Translate research insights into production-ready solutions, ensuring scalability, robustness, and efficiency 
  

• Optimize deep learning models for real-time inference on automotive-grade hardware 
  

• Design and execute evaluation, benchmarking, and validation of perception models across real-world datasets and simulation environments 
  

• Collaborate closely with cross-functional teams to integrate perception models into the full self-driving stack 
  

• Contribute to data curation, annotation strategies, and scalable training pipelines to accelerate perception development 
  

• Drive engineering excellence by writing high-quality, efficient, and well-tested code 
  
• Stay current with latest advances in computer vision, deep learning, robotics, and foundation models, and contribute to publications and patents when possible 
  

• MSc/PhD in Computer Science, Electrical Engineering, Robotics, or a related field, with 5+ years of relevant industry experience 
  

• Strong foundation in machine learning, computer vision, and 3D geometry 
  

• Hands-on experience with 3D object detection/tracking architectures 
  

• Familiarity with foundation models for vision or multimodal learning (e.g., large-scale pretraining, transfer learning, self-supervised learning etc.) 
  

• Proficiency in Python and/or C++, with expertise in modern ML frameworks (PyTorch, TensorFlow) 
  
• Experience in handling 3D point cloud data  
  
• Knowledge of multi-sensor calibration and fusion techniques 
  

• Strong software engineering skills with emphasis on scalability, reliability, and performance optimization 
  

• Ability to take algorithms from research to deployment in production systems 
  

• Excellent problem-solving skills, creativity, and ability to work in fast-paced, collaborative environments 
  

• Experience with autonomous driving or ADAS perception systems 
  

• Background in SLAM, 3D reconstruction, occupancy networks, or sensor simulation  
  

• Track record of publications in top-tier conferences