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
  state-of-the-art
  deep learning models for motion prediction in multi-agent, interactive driving scenarios

• 
  Design and implement spatiotemporal architectures such as transformers,
  GNN
  , RNNs, or diffusion models for trajectory forecasting

• 
  Fuse multi-modal
  perception
  outputs from
  camera,
  LiDAR
  and
  radar sensors into robust prediction pipelines

• 
  Build interaction-aware and scene-context models that account for traffic rules and social behaviors

• 
  Optimize
  prediction models for real-time performance on automotive embedded platforms

• 
  Validate and benchmark models against large-scale datasets and diverse simulation scenarios

• 
  Collaborate closely with
  perception
  ,
  mapping,
  planning,
  and
  other
  teams to ensure seamless integration into the
  autonomous driving
  stack

• 
  Contribute to dataset curation, annotation strategies, and scenario design for motion prediction tasks

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

• 
  Strong foundation
  in machine learning and deep learning, with emphasis on spatiotemporal modeling and trajectory forecasting

• 
  Proficiency
  in Python and
  /or
  C++, with experience in ML frameworks such as
  PyTorch
  or TensorFlow

• 
  Hands-on experience with motion prediction models (Transformers, LSTM, GNN
  etc.
  )

• 
  Familiarity with multi-modal sensor fusion and tracking systems

• 
  Solid understanding of vehicle dynamics, traffic flow modeling, and interaction-aware prediction

• 
  Experience
  optimizing
  and deploying models for real-time inference on embedded systems

• 
  Strong problem-solving skills, ability to rapidly prototype, and
  track record
  of delivering production-quality models

• 
  Familiarity with planning and control pipelines, and how prediction interfaces with downstream modules

• 
  Experience
  with
  simulation tools

• 
  Nice to have: Experience in ADAS or autonomous driving motion prediction systems