DiDi Global
Research Intern, Scene Understanding and Planning
San Jose, CA +1 · Internship · Posted Oct 18, 2026
- Location
- San Jose, CA
Mountain View, California, United States - Education
- Currently enrolled in an M.S. or Ph.D. program in a listed or related field for the full duration of the internship.
About the job
Research and develop deep learning methods that improve real-time scene understanding and planning for autonomous vehicles, from research and evaluation through integration with the planning stack.
What you'll do
- Survey research and develop practical approaches for scene understanding, prediction, and planning.
- Design, train, evaluate, and analyze deep learning models using driving logs and public benchmarks; define metrics tied to driving performance.
- Integrate validated solutions with the planning stack and collaborate with related engineering teams.
What they ask for
- Currently enrolled in an M.S. or Ph.D. program in Computer Science, Robotics, Electrical Engineering, Machine Learning, or a related field for the full internship.
- Available for a full-time, onsite internship of 3–6 months.
- Strong Python skills and experience with PyTorch or JAX.
- Hands-on deep learning model experience in computer vision, 3D perception, or sequential decision-making; solid understanding of autonomous driving fundamentals.
Nice to have
- Publications at the listed top research venues.
- Experience with sensor fusion, BEV, structured scene representations, uncertainty estimation, learning-based prediction or planning, large-scale training, autonomous driving datasets, C++, or robotics systems.
Pay
$46 per hour (base salary)
Tools
Python, PyTorch, JAX, C++, CUDA, nuScenes, Argoverse 2, Waymo Open Dataset
AI focus
Develop deep learning models for real-time driving scene understanding, prediction, and planning; train and evaluate them on driving data and benchmarks.
Model-written summary · the original posting is authoritative