My Skills

Languages:

Python, Java, Golang, C/C++, JavaScript, R, SQL, HTML, CSS, MATLAB, Fortran

Software & Frameworks:

Node.js, React.js, Tensor Flow, PyTorch, Spring Security, Spring Boot, MySQL, NumPy, Git , Linux, Django, AWS, Azure, AR/VR, ROS, Deep Learning, Machine Learning, Uneral Engine, Unity, Solid Works, NX, ABAQUS, ANSYS

Work Experiene

Human robots collaboration system design --- Amazon --- HWI Group --- Software Development Engineer

Technology Used: AWS, Java, Linux, C++

• Enhanced the Items Filtering system by developing item filters in Java for optimized food and drug arrangement, preventing contamination through bin-level segregation. Improved database schema and achieved 100% test coverage with JUnit and Mockito, successfully deploying the feature in the European production environment.
• Refactored the existing human-robot interaction platform using Carbon, React and AWS stack (SQS, SNS and API Gateway) to achieve an increase in accuracy and speed by over 5%.
• Created the SlowLion system integrating machine learning models to facilitate dynamic, optimized packaging and delivery by robots, reducing costs (500 Million Dollors) and increasing efficiency. Developed backend logic in TypeScript, deployed on AWS Lambda, utilizing S3 buckets for data storage and streamlining machine learning model feeding. Verified the system's performance through A/B and E2E testing in CodeLab.

AI-Enabled Tactical Route Planning with Real-Time Human-Robot Collaborations --- Lockheed Martin --- Student Researcher

Technology Used: ROS, PyTorch, Tensor Flow, Mono Depth, Neural Network, Res-Net, Linux, DFS, Fusion Algorithm, AR/VR

Date: 09/2021 - 12/2022

• Built a true-to-real-world environment in Unreal Engine (UE4) with drones and cameras, which reduced the cost of doing physical experiments.
• Built communication network and database for fixed cameras and drone cameras which enables real-time distributed target detection.
• Implemented Deep Learning based (Mono Depth) terrain recognition algorithm and Detectron2 algorithm applicable to RGB camera imagery, which are used to generate a depth map for obstacle avoidance and segmentation for classifications respectively.
• Used Rapidly Exploring Random Tree (RRT) algorithm for 2D path planning after achieving the obstacle map from above.
• Designed target tracking strategy for drones and ground robots using robot path planning methods.
• Designed the human-robot collaboration system (LMCO project) for agents tracking as human operators will help drones to update route for unseen obstacles like glass doors or when drones lost the target in foggy and rainy weathers.
• Created collaborative platform between human and robots where robots respond to virtual avatar controlled by human using VR autonomously.
• Analyzed images captured by virtual robot using real time key-point detection algorithm and sent control commands back to the virtual robots which enabled targets tracking and obstacles avoidance.
• Realized interaction of virtual drones and ground robots with physical targets, which is the basis for virtual interaction with the real world.
• Submitted two research papers for review.

Implementing Machine Learning for Enhanced IMCC Heat Condition Simulation --- ASML --- EI Group --- Software Development Engineer

Technology Used: FEA, CAD, Gaussian Acceleration Method, Dense Matrix Computation, Computational Fluid Dynamics, COMSOL, ANSYS

• Employed NeRF for the 3D reconstruction of IMCC and MBI cabinets using multiple images and made fine adjustments using NX.
• Designed an RNN model that transformed case boundary conditions and FEA simulation outputs into precise predictive parameters.
• Integrated FEA, Gaussian Acceleration, and RNN to optimize heat and flow distribution, improving internal layout and elevating heat dissipationefficiency by 18%.
• Certified MBI's flux compliance and found that sidewall wind tunnel performance could increase by 10% with a 1cm thickness enhancement.
• Developed a predictive RNN model for future heat condition assessments, providing proactive heat management for IMCC and MBI cabinets.

Fullstack Project Experiene

Design and Implementation of a High-Concurrency Online Learning Platform --- BiliBili --- Software Engineer

Technology Used: Distributed System, Golang, Vue.js, SQL, Docker, Portainer, Redis, Alibaba Cloud, Whisper API, Axios, Nginx

• Developed an integrated user interface using Vue.js, Golang and Gin, supporting comprehensive CRUD operations.
• Employed SQL and Redis for robust data management and caching to enhance the efficiency and speed of data retrieval, while also utilizing Axios for seamless frontend-backend communication, thereby ensuring smooth data exchange and improving overall application responsiveness.
• Leveraging Alibaba Cloud, our platform effectively handles up to 100K concurrent requests which broadens learning opportunities for Chinese by offering translated open-source courses from globally renowned institutions like CMU, Stanford, and MIT.
• Utilized Alibaba Cloud's ACR for image storage and OSS for video storage, ensuring reliable and scalable media content management.
• Configured Nginx as a reverse proxy, optimizing server load balancing and enhancing security.
• Integrated the Whisper API for handling language translations, improving user experience for international users.
• Leveraged Docker and Portainer for efficient container management, streamlining deployment and scaling processes.
• Managed codebase using Github, facilitating team collaboration and version control.

Full Stack Web Development for Car Selling Company --- AeroAutoHub --- Software Development Engineer & Cofounder

Technology Used: Javascript, Github, Node.js, Express, MongoDB, GoogleStrategy, Passport

• Used Node.js for the backend development, MongoDB for data storage, React.js for frontend, and Github for team collaborations and code management.
• Used Express for router swift and designed Admin and Client's Login system respectively with Passsport and GoogleStrategy for security.
• Implemented User-Based Collaborative Filtering recommendation system for car selling.
• Leveraged Azure for website deployment, enhancing the scalability and reliability of the platform.
• Developed a responsive ChatGPT API using Azure Functions, enabling real-time user interaction and improving customer engagement.
• Contributed to Aero Auto Company's milestone of selling over 50 cars within a single month.