Research Scientist Intern, Low-Power Scene Reconstruction for AR/VR

What you'll do

• Plan and execute research on depth estimation, occlusion, and geometric scene understanding for low-power AR/VR.
• Develop evaluation methods and run experiments on real multi-sensor device captures, measuring accuracy, stability, rendering distortion, latency, compute, and power.
• Collaborate across research and engineering teams; document and present findings and contribute to publications or patents where warranted.

What they ask for

• Currently pursuing or in the process of obtaining a PhD in computer vision, machine learning, computer graphics, robotics, or a related technical field.
• Hands-on experience in at least one listed area: depth or stereo estimation, 3D reconstruction, video or instance segmentation, or neural scene representations.
• Experience designing and running quantitative experiments, and communicating technical results.
• Intent to return to a degree program after the internship; must obtain and maintain work authorization in the country of employment.

Nice to have

• Experience with efficient or on-device inference, multi-sensor fusion, temporal filtering, AR/VR or SLAM, C++ real-time pipeline optimization, Unix, or compute and power budgeting.
• Track record of significant results, such as grants, fellowships, patents, or first-authored publications at leading workshops or conferences.

Pay

$7,650/month to $12,667/month (base salary)

Tools

TSDF, implicit or neural fields, Gaussian splatting, mobile NPU, DSP, GPU, C++, Unix

AI focus

Research lightweight learned scene representations and depth estimation for real-time AR/VR reconstruction under tight power constraints.