Deep Learning Engineer Intern – 3D Reconstruction

Job Description

Computer Vision Engineer Intern | PlusAI

The Tone:
This is an internship at PlusAI, headquartered in Silicon Valley with operations in the United States and Europe. PlusAI is a Physical AI company that builds AI-based virtual driver software for factory-built autonomous trucks. This role is crucial for developing the foundational 3D/4D digital twin technology that enables rigorous simulation and testing of autonomous driving systems, directly impacting the deployment of next-generation trucks. By contributing to advanced scene reconstruction, this intern will help accelerate the validation and verification processes essential for bringing autonomous trucking to reality.

The TL;DR
• Role: Internship
• Location: In-person, Silicon Valley, US
• Pay: $19–$65 hourly
• Team: Supports the Simulation and Perception teams
• Mission: Generate realistic 3D/4D scene reconstructions and sensor data to simulate driving environments for autonomous truck development and testing.
• Tech Stack: PyTorch, Tensorflow, Jax, 3D Gaussian Splatting (3DGS), NeRFs, camera, LiDAR, IMU, GPS

What You’ll Actually Do
• Construct Digital Twins: Develop and optimize pipelines to reconstruct high-fidelity, multi-modal 3D representations of key driving routes using recorded vehicle data including camera, LiDAR, IMU, and GPS.
• Implement Next-Gen Tech: Apply state-of-the-art neural rendering and view-synthesis techniques, such as 3D Gaussian Splatting (3DGS) and NeRFs, to handle challenging real-world lighting, weather, and dynamic objects.
• Drive Validation & Verification (V&V): Integrate reconstructed environments into our perception testing framework to stress-test object detection, tracking, and edge-case scenarios.
• Evaluate Multi-Modal Accuracy: Ensure alignment and geometric consistency between different sensor modalities within the reconstructed digital twin.
• Collaborate & Scale: Work closely with the Simulation and Perception teams to turn research prototypes into robust, scalable tooling that directly impacts our production deployment timeline.

The Must-Haves
• Background: Student pursuing a Master’s or PhD degree in Computer Science, Electrical Engineering, mathematics, statistics, or a related technical field.
• Experience: Prior experience implementing deep learning models in at least one deep learning framework.
• Skills: Deep understanding of machine learning principles and methodologies, experience with deep learning frameworks (PyTorch, Tensorflow, Jax).
• Bonus: Past experiences in deep learning projects involving object detection, motion tracking or semantic segmentation, experience with 3D Vision, or a publication record in relevant venues (CVPR, ICLR, ICCV, ECCV, NeurIPS, AAAI, SIGGRAPH).