Research Scientist / Engineer: 3D Vision & Sensor Fusion

← Back to Careers

Research Scientist / Engineer: 3D Vision & Sensor Fusion

Seoul Gangnam (On-site)

• Full-time·Talent Pool / Year-round Interest

About The Role

FRIDAY must understand geometry, motion, and uncertainty while moving through a changing factory. We are building a talent pool of engineers who can create consistent 3D state from cameras, inertial sensors, encoders, force sensors, and robot kinematics.

You will develop calibration, localization, mapping, scene reconstruction, occupancy, tracking, and state-estimation systems that support safe navigation and precise manipulation. The output of your work will be consumed directly by planning and control, so accuracy, latency, observability, and graceful degradation matter equally.

Key Areas

3D reconstructionSLAM / VIOCalibrationSensor fusionOccupancy & scene representationState estimationLocalization

What You'll Do

• Develop camera, IMU, encoder, force, and robot-state calibration and synchronization pipelines.
• Build real-time localization, SLAM/VIO, object-level tracking, 3D reconstruction, and occupancy representations.
• Design probabilistic estimators and uncertainty interfaces for downstream planning and control.
• Create tools and datasets for calibration health, drift detection, replay, benchmarking, and regression testing.
• Deploy on FRIDAY and investigate failures caused by motion blur, occlusion, reflective surfaces, vibration, and sparse observations.

Required Qualifications

• BS, MS, or Ph.D. in Robotics, Computer Vision, Electrical Engineering, Computer Science, or equivalent experience.
• Strong foundation in 3D geometry, linear algebra, probability, estimation, and numerical optimization.
• Experience implementing at least one of SLAM, VIO, calibration, 3D reconstruction, tracking, or multisensor fusion.
• Strong C++ and/or Python skills and experience profiling real-time systems.
• Ability to validate estimators using ground truth, residuals, observability analysis, and downstream task metrics.

Preferred Qualifications

• Experience with factor graphs, filtering/smoothing, differentiable geometry, or learned state estimation.
• Experience with articulated robots, eye-in-hand cameras, mobile manipulation, or dynamic scenes.
• Experience with GPU-accelerated point-cloud, voxel, neural-field, or occupancy processing.
• Familiarity with ROS/ROS2, time synchronization, PTP, camera drivers, and embedded sensor pipelines.
• Experience operating perception systems in factories or other difficult real-world environments.

What We Offer

• Competitive compensation based on experience, level, and technical impact.
• The tools, compute, robots, and equipment needed to do your best work.
• The opportunity to build, test, and deploy directly on FRIDAY and the Holiday Robotics full stack.
• Close collaboration with researchers and engineers across hardware, control, simulation, learning, perception, data, and operations.

This is an evergreen talent-pool posting. We review profiles continuously, and the timing and level of a formal hiring process may depend on team priorities and available openings. If your work matches our direction, we would still like to hear from you.

Apply