Computer Vision Engineer, 3D

Sourced from emploive.com

Mecka AI builds the data infrastructure layer for robotics and embodied AI, operating global data capture, labeling, and hardware-enabled workflows for leading AI labs and robotics companies. The company is hiring a coding-heavy Computer Vision Engineer to own the classical CV side of the stack, turning raw per-frame model predictions into clean, rigid, smooth, correctly-calibrated 3D spatial data, with an immediate focus on the 3D hands pipeline. You will partner closely with research teams — understanding their models without training them — and serve as the go-to classical computer vision specialist across the organization.

• Own the classical 3D geometry that places reconstructions correctly in space: multi-view geometry, triangulation, PnP, camera calibration, undistortion, and reprojection
• Design and tune temporal filters (low-pass, Kalman-family, interpolation) that remove jitter without losing real motion
• Run inverse kinematics and enforce physical constraints such as bone-length rigidity so reconstructed skeletons stay valid
• Turn model output into clean delivered data, including per-frame results, reports, and QA metrics that gate delivery at scale
• Build visualizers and dashboards to inspect trajectories, overlays, and failure cases
• Act as the go-to engineer for classical computer vision problems across the pipeline