シニアコンピュータビジョン／機械学習エンジニア・Digital Twin Platform
Core
Designing and optimizing deep learning models for object detection, multi-object tracking, and action recognition to support logistics, distribution centers, and factory operations within Woven City.
Role type
Senior IC Computer Vision/Machine Learning Engineer
Builds
Scalable perception pipelines and real-time CV/ML inference systems for industrial environments
Domain
Industrial automation, logistics, and smart city infrastructure
Deliverable
production ML models
Required skills
Deep learning model design and training, PyTorch or TensorFlow, scalable perception pipeline development, end-to-end production system deployment, technical leadership and architecture definition, classical computer vision geometry
Preferred skills
PhD in CV/ML, person pose estimation and skeleton-based action recognition, edge inference optimization (TensorRT, ONNX, quantization, pruning), LiDAR and 3D sensor fusion, warehouse/factory domain experience, space utilization analysis, video annotation pipelines, top-tier conference publications, Vision-Language Models, cloud platform experience
Technologies
PyTorch, TensorFlow, TensorRT, ONNX, AWS, GCP
Responsibilities
Design and optimize deep learning models for object detection, tracking, and action recognition; Build and operate real-time CV/ML inference pipelines; Lead dataset strategy, annotation standards, and model evaluation; Define technical roadmap and architecture for the CV/ML ecosystem; Mentor engineers and establish best practices
Seniority
Senior, hands-on IC with technical leadership