About the role#
Future AR and VR devices require smaller form factors, which means tighter power budgets. Current depth estimation techniques often target datacenter GPUs or mobile silicon with more power headroom than glasses allow. We are building the next generation imaging and reconstruction stack to close this gap. As a Research Scientist Intern, you will own an open research problem, choose your methods, and build evaluations for real-time scene reconstruction.
What you'll do#
- Plan and execute research to advance low-power, real-time scene reconstruction for AR/VR, including depth estimation, occlusion, and geometric scene understanding.
- Explore if a shared, learned scene representation can serve multiple downstream consumers at different latency and accuracy points.
- Define evaluation methodology and run experiments measuring geometric accuracy, temporal stability, rendering distortion, latency, and compute cost on real multi-sensor device captures.
- Collaborate with researchers and engineers across passthrough, scene understanding, and on-device compute teams to assess feasibility within headset and glasses power envelopes.
- Document and present findings, and contribute to publications and patents where the results warrant it.
What you'll need#
- Currently pursuing a PhD in computer vision, machine learning, computer graphics, robotics, or a related technical field.
- Knowledge and hands-on experience in at least one of: depth or stereo estimation, 3D reconstruction (TSDF, implicit or neural fields, Gaussian splatting), 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.
- Proven track record of achieving results through grants, fellowships, patents, or first-authored publications at leading venues like CVPR, ICCV, SIGGRAPH, or NeurIPS.
- Experience with efficient or on-device inference, such as quantization, distillation, pruning, or deployment to mobile NPU, DSP, or GPU targets.
- Experience with multi-sensor fusion across heterogeneous sensors, camera calibration, and cross-sensor registration.
- Experience with temporal filtering and state estimation over scene state.
- Familiarity with AR/VR passthrough, reprojection, occlusion rendering, or SLAM and scene reconstruction.
- Experience with C++ and profiling or optimizing real-time computer vision or graphics pipelines.
- Experience working in a Unix environment and reasoning about compute and power budgets as a design constraint.
- Must obtain and maintain work authorization in the country of employment.
Location & details#
- Locations: Redmond, Washington and Burlingame, California.
- Modality: On-site.
- Employment: Full-time intern.
- Term: Rolling.
About Meta
Meta develops software and social media applications. It operates platforms such as Facebook, Messenger, Instagram, and WhatsApp. The company maintains headquarters in Menlo Park, California. Current work focuses on augmented and virtual reality alongside artificial intelligence and machine learning.
How to get in at Meta
Landing an internship at Meta requires a proactive approach to the application process. Intern Insider sends an instant alert the moment a role matching your target is published, allowing you to apply among the first. Early applicants often have their materials reviewed before the applicant pool grows significantly. You can use Intern Insider to surface the recruiters behind specific roles at Meta. Reaching out directly to these individuals to ask about the position or a referral often improves your response rates compared to applying into a queue.
