Research Scientist: Spatial AI & 3D Reconstruction

Mecka AI; New York (NY); On-site; USD 120,000 - 150,000; Full time

Job summary

Mecka AI in New York is looking for a Research Scientist to develop proprietary models for spatial and temporal intelligence. This role emphasizes building in-house 3D reconstruction architectures and robust optical flow models using proprietary ground-truth data.

The successful candidate will tackle novel AI challenges and create state-of-the-art models with significant autonomy. You will capitalize on advanced training data to enhance perception in robotic systems.

Qualifications

• Deep expertise in Deep Learning, 3D Computer Vision, and Temporal/Video Modeling.
• Proven experience training large-scale vision models from scratch.
• Strong understanding of feed-forward 3D networks and dense motion estimation.
• Mastery of PyTorch and deep learning scaling frameworks.
• Comfortable operating in a fast-paced environment.

Responsibilities

• Architect and train proprietary foundation models from scratch.
• Design, implement, and train state-of-the-art networks for 3D geometry extraction.
• Build and train custom optical flow architectures.
• Rapidly prototype and deploy new models for various AI challenges.
• Connect model outputs into highly optimized reconstruction pipelines.

Skills

Deep Learning

3D Computer Vision

Temporal/Video Modeling

PyTorch

Data Curation

Job description

Mecka AI in New York is looking for a Research Scientist to develop proprietary models for spatial and temporal intelligence. This role emphasizes building in-house 3D reconstruction architectures and robust optical flow models using proprietary ground-truth data.

The successful candidate will tackle novel AI challenges and create state-of-the-art models with significant autonomy. You will capitalize on advanced training data to enhance perception in robotic systems.