Video Algorithms Intern, Video Coding (Gaussian Splatting), Fall 2026
Skills and tasks
Suggested skills
- Custom CUDA Kernel Optimization for Gaussian Rasterization
- Neural Video Compression & Rate-Distortion Theory
- Perceptual Quality Metrics for 3D Novel-View Synthesis
Skill-to-task connections are not available yet.
Tasks from the posting
Explore GS model compression strategies
You + AICharacterize trade-offs among GS model size
You + AIIdentify strategies to reduce training time
Your edgeDesign and implement a proof-of-concept
You + AIContribute to dataset needs for scenes
Your edge
Prepare for this role
Practice an interview or plan your next steps with AI Coach.
Application and training
Interview prep includes this job. AI Coach opens with a draft question. Apply with your existing resume
More analysis and source details
70% is classified as human or shared work.
Your edge · 3 things
- Formulating original algorithmic approaches to compress 3D Gaussian representations.
- Evaluating visual perceptual quality artifacts that standard automated metrics miss.
- Architecting end-to-end proof-of-concept renderers for consumer playback hardware.
Demand for spatial computing and 3D/4D photorealistic rendering is accelerating across hardware vendors and streaming platforms. Efficient compression of novel-view synthesis models is essential for bandwidth-constrained consumer playback.
Do this week
- Custom CUDA Kernel Optimization for Gaussian RasterizationDirect GPU programming expertise significantly increases your market value and research output speed in neural graphics.
- Neural Video Compression & Rate-Distortion TheoryCombining traditional video coding principles with 3D computer vision makes you uniquely qualified for senior streaming algorithm roles.
- GitHub CopilotWriting PyTorch model wrappers and evaluation boilerplate for Gaussian Splatting
Scan another job
Hiring for a role like this? See how teams use scans to write clearer job posts.