Research Scientist — 3D Reconstruction & Neural Rendering

Mecka; New York (NY); On-site; USD 141,000 - 162,000; Full time

Job summary

Mecka invites a Research Scientist to architect and train proprietary 3D reconstruction pipelines from scratch, turning real-world multi-modal data into photorealistic digital environments using methods like 3D Gaussian Splatting and NeRFs.

You will integrate these environments into the perception pipeline, optimize assets for high fidelity interactive viewing, and support downstream robotics work with scalable training.

Qualifications

• Expertise in 3D computer vision, neural rendering, and spatial modeling.
• Experience training and scaling large-scale 3D vision models with PyTorch on multi-terabyte datasets.
• Experience writing custom CUDA kernels for 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 of real-world environments to improve downstream robotics pipelines and world models.
• Client Delivery & Viewer Optimization: Compress and optimize 3D scene representations for high-framerate rendering in client viewers with interactive capabilities.
• Emergent Perception R&D: Prototype new architectures to isolate dynamic actors and fuse new sensor data.

Skills

3D vision

PyTorch

Neural rendering

Multi-view geometry

Tools

CUDA kernels

Job description

Mecka invites a Research Scientist to architect and train proprietary 3D reconstruction pipelines from scratch, turning real-world multi-modal data into photorealistic digital environments using methods like 3D Gaussian Splatting and NeRFs.

You will integrate these environments into the perception pipeline, optimize assets for high fidelity interactive viewing, and support downstream robotics work with scalable training.