Research Scientist / Engineer: Robotics Perception

← Back to Careers

Research Scientist / Engineer: Robotics Perception

Seoul Gangnam (On-site)

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

About The Role

We are building a talent pool of perception engineers who can turn raw visual and tactile signals into reliable state for manipulation. You will develop real-time perception capabilities that help FRIDAY find, track, grasp, and interact with objects in cluttered industrial environments.

The role covers object detection and tracking, 6D pose estimation, segmentation, affordance and grasp estimation, tactile perception, and foundation-model adaptation. You will own the path from dataset and model to an optimized runtime that works under occlusion, changing lighting, motion, and sensor noise.

Key Areas

Object detection & tracking6D pose estimationSegmentationAffordance & grasp perceptionTactile sensingFoundation-model optimizationEdge inference

What You'll Do

• Build real-time perception models and pipelines for objects, hands, tools, workpieces, and human activity around the robot.
• Develop 6D pose, segmentation, tracking, affordance, grasp, and contact-estimation capabilities.
• Fuse camera and tactile signals with robot state, and expose calibrated uncertainty to planning and control.
• Curate datasets, define annotations and benchmarks, and use synthetic data where it improves coverage.
• Optimize and deploy models on robot compute; diagnose latency, drift, occlusion, and domain-shift failures in the field.

Required Qualifications

• BS, MS, or Ph.D. in Computer Vision, Machine Learning, Robotics, Computer Science, or equivalent experience.
• Strong understanding of modern deep learning for visual perception and experience with PyTorch or a similar framework.
• Experience with at least two of detection, segmentation, tracking, pose estimation, metric learning, or multimodal fusion.
• Strong Python skills and the ability to write production-quality data, training, and inference code.
• Ability to evaluate model quality against downstream robot behavior, not only offline accuracy.

Preferred Qualifications

• Experience with RGB-D, stereo, fisheye, event cameras, or tactile sensors.
• Experience optimizing inference with TensorRT, ONNX, CUDA, quantization, or distillation.
• Experience with vision-language or segmentation foundation models and domain adaptation.
• Experience deploying perception on manipulators or mobile robots in industrial environments.
• Experience with synthetic data generation, active learning, or uncertainty calibration.

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