Research Scientist – Hand Tracking & Manipulation

The role

This person will architect and train proprietary foundation models for 3D hand tracking and articulated pose estimation. They will develop interaction models for egocentric manipulation and build models for 3D hand pose estimation and dense mesh recovery.

What you will do

• Design, implement, and train networks for 3D hand pose estimation, dense mesh recovery, and kinematic tracking.
• Scale multi-view and temporal ML architectures across multi-GPU clusters.
• Develop novel loss functions that enforce biomechanical constraints, temporal smoothness, and physical plausibility.
• Build and train custom architectures for egocentric manipulation modeling.
• Track objects through complex grasps, segment tools from hands, and map contact points and forces.
• Rapidly prototype and deploy new models for tactile-visual fusion, fine-grained action segmentation, and novel hardware sensor integrations.
• Resolve sudden algorithmic bottlenecks in the data engine.
• Connect tracking models into pipelines that reason about physical contact surfaces and object affordances.

Required qualifications

• Deep expertise in Deep Learning, 3D Computer Vision, and Articulated Tracking / Hand Pose Estimation.
• Proven experience training large-scale vision models from scratch.
• Strong theoretical and practical understanding of parametric hand models, inverse kinematics, and dense mesh 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.

Nice to have

• First-author publications in top-tier venues (CVPR, ICCV, ECCV, NeurIPS) focusing on 3D hand tracking, hand-object interaction (HOI), dexterous manipulation, or human mesh recovery.
• Specific experience working with massive egocentric manipulation datasets (e.g., Ego4D, Ego-Exo4D, DexYCB, Epic-Kitchens).
• Experience writing custom CUDA kernels to accelerate 3D operations, differentiable rendering of meshes, or collision/contact computation.

About the company

Mecka AI is building the data infrastructure layer for robotics and embodied AI. They design and operate global systems for data capture, data labeling, and hardware-enabled workflows used by leading AI labs and robotics companies.