Research Scientist – Computer Vision (Hand Tracking & Manipulation)

Mecka AI is building data infrastructure for robotics and embodied AI, including systems for data capture, labeling, and hardware-enabled workflows. The Research Scientist will architect and train proprietary foundation models for 3D hand tracking, articulated pose estimation, and hand-object interaction, while developing perception solutions for manipulation and downstream robotics applications.

Responsibilities:

• Zero-to-One Model Development: Design, implement, and train state-of-the-art networks for 3D hand pose estimation, dense mesh recovery, and kinematic tracking
• Large-Scale Distributed Training: Scale multi-view and temporal ML architectures across multi-GPU clusters to handle massive, multi-modal datasets of human hands in action
• Loss & Architecture Innovation: Push the boundaries of current paradigms by developing novel loss functions that enforce biomechanical constraints, temporal smoothness, and physical plausibility
• Egocentric Manipulation Modeling: Build and train custom architectures capable of handling the extreme motion blur, severe self-occlusion, and rapid rotations inherent in first-person object manipulation
• Dynamic Scene Understanding: Use your models to track objects through complex grasps, segment tools from hands, and map contact points and forces to provide rich regularization for downstream action-conditioned robotics models
• Rapid Prototyping: Tackle novel, unmapped AI challenges as they arise. You will rapidly prototype and deploy new models for tasks spanning tactile-visual fusion, fine-grained action segmentation, and novel hardware sensor integrations
• Agile Problem Solving: Pivot to resolve sudden algorithmic bottlenecks in the data engine, adapting the latest research to unblock new product capabilities for our robotics customers
• Interaction Integration: Connect the outputs of your foundational tracking models into highly optimized pipelines that reason about physical contact surfaces and object affordances, directly bridging the gap between human video data and robotic control policies