Skip to main content

计算机视觉工程师,3D

Summary by AIEngineer.careers

计算机视觉工程师,3D is a Computer Vision Engineer role (full-time). with Mecka.ai. in TORONTO, CA. Imported listing (source: hirelala.com). Apply on the employer's site (hirelala.com).

Imported listing (source: hirelala.com) · Apply on hirelala.com

How our listings work

TORONTO · CA
—
Full-time
SENIOR
Apply Now

More AI jobs in Canada

The sections below reproduce the third-party job description for reference. AIEngineer.careers does not write or control this text.

Imported job description

Sourced from hirelala.com

Mecka.ai builds data infrastructure for robotics and embodied AI, operating global systems for data capture, annotation, and hardware-supported workflows used by leading AI labs and robotics companies. This role owns the classical computer vision layer of the stack, turning raw per-frame model predictions into clean, rigid, smooth, and correctly calibrated spatial data. The initial focus is the 3D hand pipeline, with the engineer becoming the organization's go-to expert for classical CV, geometry, filtering, and pipeline issues.

Responsibilities

  • Master classical 3D geometry to place reconstructions correctly in space: multi-view geometry, triangulation, PnP, camera calibration, undistortion, and reprojection
  • Design and tune temporal filters (low-pass, Kalman family, interpolation) to remove jitter without losing real motion
  • Run inverse kinematics and enforce physical constraints such as bone-length rigidity to keep reconstructed skeletons valid
  • Build checks that prevent bad frames from being delivered
  • Convert model outputs into clean delivery data, including per-frame results, reports, and QA metrics gating delivery, while keeping pipelines running at scale
  • Build visualization tools and dashboards to inspect trajectories, overlays, and failure cases
  • Serve as the go-to engineer for classical computer vision problems in the pipeline

Requirements

  • 5+ years of professional experience in software engineering and computer vision
  • Strong software engineering skills with clean, efficient, production-grade Python (C++ a plus)
  • Solid multi-view geometry: triangulation, PnP, camera calibration, reprojection, and coordinate transforms
  • Temporal filtering and signal processing: low-pass and Kalman-family filters, interpolation, and judgment on smoothness vs. fidelity tradeoffs
  • Inverse kinematics and rigid-body or bone-length constraints on joint structures
  • Enough ML knowledge to work with deep models such as pose and mesh regressors, including their outputs and failure modes, without training them
  • Data quality mindset: handling noisy real-world data and building QA that catches issues before customers do

Nice to Have

  • Human pose or mesh reconstruction (hand or body), including keypoint and mesh pipelines
  • Depth in Bayesian filtering or state estimation; experience with optimization frameworks such as Ceres or GTSAM
  • Building CV tools such as trajectory visualization tools and overlay or QA dashboards
  • Stereo, multi-view, or ego-exo capture experience
  • Lightweight temporal ML, such as small networks for smoothing or gap filling

Tech Stack

CeresC++GTSAMInverse KinematicsKalman FiltersMesh ReconstructionMulti-view GeometryPose EstimationPythonSignal Processing
Mecka.ai

Mecka.ai

Markham · CA · 65+ employees

Mecka AI is a robotics data and infrastructure company serving physical AI. It provides the data, evaluation, and deployment layer that captures, structures, and evaluates real-world human activity so robotics and embodied-AI teams can train models and move systems from research toward reliable commercial deployment.

Weekly job alert

Get a weekly email when new AI engineering jobs match your filters. Free — confirm your address to start.

Related Jobs