Research Scientist, SLAM & VIO

Mecka; New York (NY); On-site; USD 100,000 - 140,000; Full time

Benefits offered by this job

Access to proprietary data

Cutting-edge research environment

Opportunity for high impact

Job summary

Mecka is hiring a Research Scientist in New York City to architect and train proprietary models aimed at advancing spatial and temporal intelligence in robotics. You will tackle core challenges relating to 3D reconstruction and optical flow modeling.

Ideal candidates should possess deep experience in Deep Learning and 3D Computer Vision, with the ability to manage large-scale data projects. This role promises high impact and cutting-edge research opportunities.

Qualifications

• Deep expertise in Deep Learning, specifically training large-scale vision models from scratch.
• Strong understanding of feed-forward 3D networks and dense motion estimation.
• Experience with large multi-terabyte datasets for training.

Responsibilities

• Architect and train proprietary foundation models from scratch.
• Develop robust optical flow models for egocentric vision.
• Rapidly prototype new models for multi-modal sensor fusion.

Skills

Deep Learning

3D Computer Vision

Temporal Modeling

PyTorch

CUDA Programming

Job description

About Mecka AI

Mecka AI is building the data infrastructure layer for robotics and embodied AI. We partner with leading AI labs and robotics companies to deliver high-quality, real-world datasets used to train, evaluate, and deploy robotic systems—where model performance is dictated by data quality.

The Role

While our existing perception division handles classical state estimation and VIO, this role is dedicated to the next generation of spatial and temporal intelligence. We are hiring a Research Scientist to architect and train proprietary foundation models from scratch.

Your core mandate is twofold: building our in‑house equivalents to cutting‑edge 3D reconstruction architectures, and developing highly robust optical flow models tailored for the chaotic domain of egocentric vision. Beyond these core pillars, you will serve as a lead problem‑solver for emergent perception challenges as our hardware and downstream robotics needs evolve.

To achieve this, we can provide a massive, continuous stream of high-quality, proprietary ground‑truth data captured by our infrastructure. You will use this data advantage to train networks that surpass current public baselines, owning the complete spatial‑temporal perception loop for our data engine.

What You'll Work On

Architecting Proprietary Spatial Models

• Zero‑to‑One Model Development: Design, implement, and train state‑of‑the‑art feed‑forward network and per‑scene differential optimization architectures for 3D geometry extraction.

• Large‑Scale Distributed Training: Scale multi‑view ML architectures across multi‑GPU clusters to handle massive, multi‑modal spatial datasets.

• Loss & Architecture Innovation: Push the boundaries of current paradigms by developing novel loss functions and attention mechanisms tailored to our specific data distributions.

Egocentric Optical Flow & Temporal Dynamics

• Egocentric Motion Modeling: Build and train custom optical flow architectures capable of handling the extreme motion blur, rapid rotations, and sudden occlusions inherent in head‑mounted or robot‑mounted cameras.

• Dynamic Scene Understanding: Use your flow models to segment dynamic actors, track objects through complex manipulations, and provide motion regularization for downstream action‑conditioned world models.

Emergent Perception R&D

• Rapid Prototyping: Tackle novel, unmapped AI challenges as they arise. You will rapidly prototype and deploy new models for tasks spanning tracking, segmentation, multi‑modal sensor fusion, and beyond.

• Agile Problem Solving: Pivot to resolve sudden algorithmic bottlenecks in the data engine, adapting the latest research to unblock new product capabilities or hardware integrations.

Next‑Level Dense Reconstruction

• Neural Rendering Integration: Connect the outputs of your foundational models into highly optimized, large‑scale dense reconstruction pipelines (3D Gaussian Splatting, NeRFs) to generate photorealistic environments.

Who You Are

Required Background

• Deep expertise in Deep Learning, 3D Computer Vision, and Temporal/Video Modeling.

• Proven experience training large‑scale vision models from scratch, not just running inference or fine‑tuning.

• Strong theoretical and practical understanding of modern feed‑forward 3D networks and dense motion estimation.

• Mastery of PyTorch and deep learning scaling frameworks.

• Experience handling and curating massive, multi‑terabyte image and video datasets for training.

• Comfortable operating in a fast‑paced environment where priorities can shift rapidly to capitalize on new research or hardware capabilities.

Strong Signals:

• First‑author publications in top‑tier venues (CVPR, ICCV, ECCV, NeurIPS) focusing on 3D deep learning, optical flow, video generation, or spatial transformers.

• Specific experience working with egocentric video datasets (e.g., Ego4D, Ego‑Exo4D) and solving the unique optimization challenges they present.

• Experience writing custom CUDA kernels to accelerate 3D operations, ray marching, or correlation volume computations.

Why This Role?

• The Data Advantage: You will have access to a scale and quality of proprietary spatial and temporal ground truth that most academic researchers only dream of.

• Pure R&D & Model Ownership: You are not maintaining legacy systems; you are given a blank slate and the compute resources to build the state‑of‑the‑art.

• High Impact: The spatial priors and motion models you architect will directly define how the next generation of embodied AI agents perceive and move through the physical world.