Machine Learning Engineer Intern - Scenario Simulation

Team: Planning

Location: Santa Clara, CA

Commitment: Intern

Workplace Type: onsite

Responsibilities:

Bridge the Sim-to-Real Gap: Develop and implement a translation layer that converts idealized simulator Ground Truth (GT) into realistic, "noisy" Bird’s-Eye View (BEV) embeddings.

Optimize Simulation Throughput: Research and implement a "shortcut" pipeline that bypasses slow image/LiDAR rendering to generate BEV features directly from state data.

Enable Closed-Loop Training: Integrate the translated BEV embeddings into a training pipeline to make synthetic data directly usable for planning models.

Support Reinforcement Learning: Create the infrastructure necessary for planning models to undergo self-play RL fine-tuning within the bridged BEV feature space.

Required Skills:

• Strong foundation in deep learning, computer vision, and machine learning.
• Proficiency in Python and deep learning frameworks (PyTorch)
• Prior experience with BEV / E2E Autonomous Driving Architectures (understanding of BEV generation, sensor fusion, spatial transformation).
• Prior experience in addressing the Sim-to-Real Gap in autonomous systems such as robotics and autonomous driving 
  
  

Preferred Skills:

Nice-to-have:
 
• Experience with C++
• Experience with End-to-End (E2E) driving models.
  
• Experience with working with simulators (CARLA, IsaacSim, Gazebo)
  
• Experience with curating datasets and synthetic data generation (SDG), 
  
• Experience with ML Infras (Kubeflow, MLFlow, Weights & Biases, etc) 
  
• Basic understanding of simulation / scenario-based testing for autonomous driving systems