Full-stack developer, AI engineer, DevOps specialist with over 5 years of experience, delivered more than 20 projects for clients such as Tesla, Nissan, YanFeng, CASC, CASIC. Proficient in building responsive cross-platform applications, frontend to backend, with end-to-end DevOps support. Possesses strong team collaboration and client communication skills, innovative and critical thinking.
Frontend: TypeScript, React, Next.js, Vue, Tailwind, PWA, Wordpress, Capacitor.js Backend: Prisma, FastAPI, NestJS, SpringCloud, PostgreSQL, MongoDB, Redis, RabbitMQ Cloud: AWS, GCP, Cloudflare, Supabase, Firebase, Stripe DevOps: Github Actions, Docker, Kubernetes, Jenkins, GitLab, Postman 3D: Unity, Three.js, Spline, WebGL/webGPU AI Skills: Context Engineering, n8n, A2A, MCP, RAG, Fine-tuning, PyTorch
I am responsible for the design and development of an AI-driven generative system for 3D-printed footwear. The core modules include high-precision foot scanning utilizing iPhone LiDAR and binocular cameras, an AI engine for parameter-driven shoe last generation based on foot morphology, an automated CAD workflow for upper and sole optimization, and an integrated algorithm for the automatic generation of lattice structures from CAD models. I plan to submit a research paper on this work in the first half of next year.
Founded a personal software company, Oiy AI, and independently delivered multiple enterprise-level AI Agent projects, such as the voice custom services agent Ringbot, the open source learning agent Learnify, and a customized fire safety report drafting agent, among others.
Led a technical team of 22 people at the Nanjing R&D Center, reporting directly to the CTO. Directed the restructuring of the team into project-based units, adopted agile methodologies, and introduced AI-assisted programming to all teams, resulting in a 60% increase in development efficiency. Implemented stand-up meetings, code reviews, automated DevOps workflows and containerized deployment, achieving an 85% reduction in customer-reported issues.
I contributed to the development of a B/S architecture PLM system, where I played a key role in the development of many core functions.
Developed many Siemens Teamcenter projects with more than 100 complex functional modules. Developed several B/S projects.
An AI-powered learning tool that can help users learn everything faster and better.
User can upload files in different formats (PDF, Word, Excel, PPT, Images, Youtube Links, etc) and Learnify will generate syllabus, mind maps, summary notes, flashcards, quizzes, podcasts and more.
What's even better is user can get 1v1 teaching experience by rasing inline AI chats in Notes, asking for detailed explanation in Quizzes, joining podcast as a guest then starting a real-time chat with the host.
My Contribution
It's an open-source project (https://github.com/oiy-ai/learnify). I founded it by myself and contributed everything. Besides feature development, I also:
Tech Stack
Frontend: React, Next.js, Tailwind, PWA, Lit, Electron, Capacitor
Backend: Prisma, NestJS, PostgreSQL, pgvector, GraphQL, Redis, webRTC
AI: OpenRouter, Claude Code, IndexTTS, LangGraph, pgvector, Vertex AI
DevOps: Docker, Kubernetes, Github Actions, GCP, Cloudflare, Supabase, Upstash
Ringbot is an AI VoiceAssistant for Effortless Reservations. She has a natural voice and can help users to make reservations on phone calls or web voice chat.
It's built by a startup company in Melbourne. And they are building the prototype with several local enterprises like Okami, MC Dental.
My Contribution
I was in charge of the entire application development, including the frontend, backend, low-latency audio2audio AI integration, A2A workflow design, RAG and DevOps.
Tech Stack
TypeScript, React, Next.js, Tailwind, PWA, Radix UI, shadcn/ui, Magic UI, webRTC, OpenAI Realtime API, LangGraph, Docker, Github Actions, GCP, Cloudflare Worker and R2, Supabase, Upstash, OpenRouter, pgvector, PostgreSQL, Prisma, GraphQL, Redis
A cross-platform 3D model viewer for manufacturing with JT format support. Key features include parameter/annotation preservation, efficient BOM-based multi-file rendering (90% time savings), dynamic hot-reload updates, and virtualized rendering for giant models with 100,000+ parts.
My Contribution
As the sole developer, I architected and implemented all core functionalities from the ground up, including the complete codebase development. I also served as the primary technical liaison with Siemens support team.
Tech Stack
Three.js, WebGL, Vue, Siemens JT Toolkit, Siemens Vis Web, Docker
A self-developed Product Lifecycle Management (PLM) platform. Benchmarking against Siemens Teamcenter, it covered over 70% of the features and in most features it's faster than Teamcenter. It earned over 10 million RMB in enterprise contracts within the first year after launch.
My Contribution
I'm the technical lead of this team. I'm responsible for the technical architecture, system design, and development of the core features. I also in charge of the agile iteration, weekly public release, and delivery management.
Tech Stack
Frontend: TypeScript, Vue, Electron, WebGL, Three.js, Micro-frontend
Backend: SpringCloud, MySQL, MongoDB, Redis, RabbitMQ, Kafka
DevOps: Docker, Kubernetes, Gitlab, Jenkins
Delivered many enterprise-level PLM/PDM projects based on the Wonder Insight platform. Client list includes leading companies in the aerospace, aviation, and machinery industries. Some of the projects are listed below:
My Contribution
As the leader of the product development team, provide project technical support and communicate with the implementation team.
Tech Stack
Same as Wonder Insight.
Delivered many enterprise-level PLM/PDM projects based on Siemens Teamcenter. Client list includes leading companies in the aviation and machinery industries. Some of the projects are listed below:
My Contribution
Developed many features of those projects. In some projects, I'm in charge of one or two entire modules on my own.
Tech Stack
Teamcenter, Java, SWT, SpringBoot
AI Manufacturing Process Generation: a system using LLM and RAG to generate manufacturing processes, involving data cleaning and annotation of over 10 years of historical process data.
Yanfeng LEMS project: I was in charge of two modules: abnormal monitoring of ambient light using OpenCV, failure analysis using RAG.
Wonder Microweb: a micro frontends framework that enables seamless integration of diverse frontend technologies such as React, Angular, Vue and Next.js base on Web Components. It offers advanced features including data communication, global context management, unified virtual routing, unified API, prefetching.
Wonder Table: a Vue table component using virtualization that supports the smooth display of 100,000+ rows and 100,000+ columns without pagination, with powerful functions like filtering, sorting, editing, dragging, tree data support etc.
Summer Research Scholarship - Nov 2025
Software Engineer - Apr 2024
Founder & Team Leader - Oct 2017
Ministry of Education, China - Credential ID 201710332078
Certification - Aug 2017
Suzhou Human Resources and Social Security Department
2nd Prize - Jun 2018
Suzhou University of Science and Technology
Person of the Year - Dec 2017
Suzhou University of Science and Technology
3rd Prize - Sept 2017
Jiangsu Education Department
1st Prize - Jun 2017
Suzhou University of Science and Technology
1st Prize - May 2017
Suzhou University of Science and Technology
1st Prize - Nov 2016
Suzhou University of Science and Technology