3D Reconstruction Scientist: Photoreal Environments

Research Scientist – 3D Environment Reconstruction

Richmond Hill

On-site

CAD 120,000 - 190,000

Full time

14 days+

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Job summary

Mecka AI is seeking a Research Scientist to architect and train proprietary 3D reconstruction pipelines from scratch. You will transform continuous streams of real-world multi-modal data into accurate, photorealistic digital environments using 3D Gaussian Splatting and NeRFs.

You will integrate these environments to improve perception pipelines and optimize spatial assets for client delivery and interactive viewing.

Qualifications

Deep expertise in 3D Computer Vision, Neural Rendering, multi-view geometry, and spatial modeling.
Proven experience training and scaling large-scale 3D vision models from scratch using PyTorch and multi-terabyte datasets.
Experience writing custom CUDA kernels to accelerate 3D operations, ray marching, or rasterization.

Responsibilities

Advanced Neural Reconstruction: Design, train, and scale state-of-the-art models for dense 3D geometry extraction across multi-GPU clusters.
Sim-to-Real Integration: Reconstruct high-fidelity digital twins to improve downstream robotics pipelines, world models, and sim-to-real training.
Client Delivery & Viewer Optimization: Compress and package 3D scenes for high-framerate rendering in client viewers.
Emergent Perception R&D: Prototype architectures to isolate dynamic actors and fuse new hardware sensor data.