{"username":"jhyan","header":{"name":"JunhaoYan","tagline":"Backend & AI Engineer with experience in computer vision, industrial software, AI agents, and hardware-software integration."},"personalInfo":{"email":"jhyan0908@outlook.com","phone":"13048737072","location":"Shenzhen, China"},"experience":[{"company":"Independent / Entrepreneurship","role":"Founder & AI Product Developer","startDate":"2024.10","endDate":"Present","bullets":["Explored B2B AI opportunities in manufacturing after leaving XKL, speaking with factory owners to identify practical AI adoption points and workflow bottlenecks.","Built AICad, an AI-agent product for CNC manufacturing workflows including CAD drawing translation, drawing review, quotation assistance, and version comparison.","Owned backend architecture and implementation end to end while coordinating outsourced frontend work, covering requirements, system design, coding, testing, and demo delivery.","Designed a modular backend using Python, FastAPI, LangGraph, an API layer, business-processing layer, agent library, and persistence layer."],"tags":["Python","FastAPI","LangGraph","AI Agents","Backend","Manufacturing AI"]},{"company":"Shenzhen Xinkailai Technology (XKL)","role":"Software Development Engineer","startDate":"2023.03","endDate":"2024.10","bullets":["Worked primarily on YMS, an AFM upper-computer software project targeting domestic replacement of atomic force microscope equipment.","Led or independently completed requirement walkthroughs, design, implementation, integration, simulator testing, and clean-room real-machine validation for new features and version quality.","Owned algorithm-module work, developing and integrating multiple data-analysis algorithms and validating them on both simulators and physical equipment.","Implemented hardware adaptation and driver-layer integration in C++ for line-scan and area-scan workflows, improving device interaction stability and performance.","Developed upper-computer service features with Java and Spring Boot, including API design, business logic, and system integration.","Delivered dozens of requirements across 10+ version iterations with no rejected releases, supporting product milestones and customer acceptance."],"tags":["Java","Spring Boot","C++","Industrial Software","Algorithms","Hardware Integration"]},{"company":"National Research Canada","role":"Computer Vision Research Intern","startDate":"2020.10","endDate":"2021.10","bullets":["Led development of a deep-learning based inspection workflow for aircraft component testing, reducing manual inspection effort through automated image analysis.","Collected RGB camera images, labeled and filtered data with LabelMe, and built a PyQt5 desktop UI for detection results, alerts, live camera view, and before/after image comparison.","Trained and deployed PyTorch and scikit-learn models including DeepLabV3 with a ResNet18 backbone and a random-forest digit detector.","Combined contrastive-learning pretraining, CNN refinement, Adam optimization, and exponential learning-rate scheduling to improve model performance."],"tags":["PyTorch","DeepLabV3","OpenCV","PyQt5","Computer Vision","Python"]},{"company":"Lavia Solution","role":"Computer Vision Intern","startDate":"2020.06","endDate":"2020.09","bullets":["Helped build an automatic acne annotation system in the R&D department, focusing on model training for acne recognition.","Annotated image data with LabelMe and trained a Mask R-CNN based detector using Detectron, applying NMS to produce final candidate regions.","Reduced repetitive manual work for skin analysts by automating part of the image-labeling and analysis workflow."],"tags":["Mask R-CNN","Detectron","Computer Vision","LabelMe","Python"]}],"education":[{"school":"University of Ottawa","major":"Electrical and Computer Engineering","degree":"Master of Engineering","startDate":"2018.09","endDate":"2022.11"},{"school":"University of Shanghai for Science and Technology","major":"Optical Information Science and Engineering","degree":"Bachelor of Engineering","startDate":"2014.09","endDate":"2018.09"}],"projectsRecent":[{"title":"AICad","description":"AI-agent product for CNC manufacturing workflows, covering CAD drawing translation, drawing review, quotation support, and version comparison. Sole backend owner; delivered an end-to-end demo with Python, FastAPI, and LangGraph.","url":"https://jhyan.xyz/work/carrer.html","tags":["AI Agents","FastAPI","LangGraph","Backend","Manufacturing"]},{"title":"YMS / AFM Upper-Computer Software","description":"Industrial software project at XKL for an AFM product. Delivered algorithms, C++ driver-layer integration, Java/Spring Boot service features, simulator testing, and clean-room real-machine validation across 10+ releases.","url":"https://jhyan.xyz/work/carrer.html","tags":["Java","Spring Boot","C++","Industrial Software","AFM"]},{"title":"Domain Adaptation for Semantic Segmentation","description":"First-author arXiv research proposing Separate Affine Transformation in Batch Normalization for unsupervised domain adaptation in semantic segmentation.","url":"https://arxiv.org/abs/2110.07376","tags":["Computer Vision","Semantic Segmentation","Domain Adaptation","PyTorch"]}],"projectsDetailed":[{"title":"Domain Adaptation on Semantic Segmentation with Separate Affine Transformation in Batch Normalization","type":"Research Publication","startDate":"2019.09","endDate":"2021.09","url":"https://arxiv.org/abs/2110.07376","award":"First Author","bullets":["Proposed Separate Affine Transformation (SEAT), replacing shared BatchNorm affine parameters with domain-specific affine parameters for source and target domains.","Used DeepLabV3 with a ResNet101 backbone and adversarial training for unsupervised domain adaptation in semantic segmentation.","Evaluated on GTA5 and SYNTHIA as source domains and Cityscapes as the target domain, improving performance by 4.0 mIoU in reported experiments.","Published as arXiv:2110.07376 with co-author Woonsok Lee."],"tags":["PyTorch","DeepLabV3","ResNet101","GAN","Batch Normalization","Semantic Segmentation"],"externalLink":{"label":"arXiv","url":"https://arxiv.org/abs/2110.07376"}},{"title":"DeepLabV3 Defect Detection System","type":"Computer Vision Project","startDate":"2020.10","endDate":"2021.10","url":"https://jhyan.xyz/work/carrer.html","bullets":["Built an automated defect/corrosion inspection system for high-temperature aircraft components.","Implemented a two-stage detection pipeline: DeepLabV3 semantic segmentation for coarse corrosion-region detection, followed by multi-layer convolutional edge detection for boundary refinement.","Reached precision and recall of at least 95% according to project records.","Coordinated requirements and data collection with the client, decomposed tasks, assigned work to lab members, and delivered the project on schedule."],"tags":["DeepLabV3","Computer Vision","OpenCV","PyTorch","Defect Detection"]},{"title":"Embedded Aluminum Measurement System","type":"Embedded Systems Internship","startDate":"2016.06","endDate":"2016.09","bullets":["Developed an embedded measurement system for aluminum products at Huizhou Lichang Aluminum Products Co., Ltd.","Used an STM32 development board to control motor-driven conveyor movement and infrared sensors.","Calculated product length from conveyor speed and sensor timing, reducing manual measurement effort and improving measurement efficiency."],"tags":["STM32","Embedded Systems","C","Sensors"]},{"title":"Unity Target-Seeking Projectile","type":"Course Project","startDate":"2020.01","endDate":"2020.04","bullets":["Built a Unity simulation environment with vegetation, characters, buildings, and turret behavior.","Implemented movement and action logic in C# and trained a target-seeking projectile with Q-learning."],"tags":["Unity","C#","Q-learning","Reinforcement Learning"]}],"skills":[{"name":"Backend & Systems","items":["Python","FastAPI","Java","Spring Boot","C++","REST APIs","Modular Architecture","Hardware Integration"]},{"name":"AI & Computer Vision","items":["PyTorch","OpenCV","scikit-learn","DeepLabV3","ResNet","Mask R-CNN","YOLO","Detectron","Semantic Segmentation","Domain Adaptation"]},{"name":"AI Agents","items":["LangGraph","Workflow Orchestration","Agentic Backend Design","Manufacturing AI","CAD Workflow Automation"]},{"name":"Tools & Communication","items":["LabelMe","PyQt5","Unity","Git","English working communication","IELTS 6.5"]}],"contact":[{"label":"GitHub","url":"https://github.com/jhyan-ux"},{"label":"Blog","url":"https://jhyan.xyz/"},{"label":"Email","url":"mailto:jhyan0908@outlook.com"},{"label":"arXiv","url":"https://arxiv.org/abs/2110.07376"}],"meta":{"updatedAt":"2026-05-21T00:23:32.840Z"}}