Skip to main content

Yixiang Zhou
Software & Data Engineer | IT Support | NLP & Policy Analysis

💼 Currently working as a Technical Support Engineer at Optix, providing AI solutions and technical support to clients. I recently graduated with a Master's degree in Computer Science from Northeastern University, specializing in software development, data analysis, and IT support. I thrive at the intersection of code and communication — building reliable systems and helping users solve complex issues.

About Me

💻 My experience includes working on LLM-based classification pipelines using NLP and LangChain, full-stack Java/JavaScript development for digital platforms, and cross-functional support in fast-paced environments. I've also gained hands-on skills in SQL, Python, Linux, and cloud tools like Azure and EC2.

🧠 I enjoy learning new technologies, writing clean code, and improving systems through both development and support. With an academic background in English, Spanish, and Computer Science, I bring a well-rounded and globally-minded approach to problem-solving.

🌱 Always excited to grow in roles related to software, data, or technical support — and to contribute meaningfully as part of a collaborative team.

Education

Sep 2023 - Apr 2025
Northeastern University Vancouver
Master of Computer Science | GPA: 3.71/4.0
Sep 2021 - Jan 2022
University of Western Ontario, Huron University College
Exchange Student Program with Full Scholarship
Sep 2019 - Jun 2023
Beijing Language and Culture University
Bachelor of Arts, major in English and Spanish | GPA: 3.77/4.0

Professional Experience

June 2025 - Present
Technical Support Engineer
Optix. Vancouver, Canada

Technical Support Engineer

Key Accomplishments Resolved 800+ customer inquiries and technical issues across billing, automation, and third-party integrations (Stripe, Kisi, GraphQL, MySQL). Collaborated with the mobile engineering team and admin leads to bridge communication between business and technical workflows in the WLA (Workspace Login & Access) build process. Partnered with product and engineering teams to identify and fix systemic problems, improving first-response accuracy by 37% and ticket resolution time by 29%. Enhanced Felix, Optix's AI-powered support bot, by refining contextual understanding and implementing MCP (Model Context Protocol) integrations. Increased bot engagement rate by 45%, automated resolution rate by 33%, and improved overall CX score by 18% through better intent detection and message routing. Supported dev team the Coworking Software Dashboard with UI/UX improvements. Developed and optimized front-end components using React and Tailwind CSS, improving dashboard load time by 22% and modernizing admin workflows based on customer feedback. Built AI-driven solutions to enhance Optix's B2B SaaS operations — designed and deployed custom MCP connectors enabling secure context retrieval from Productboard, Intercom, and internal analytics systems. Accelerated AI response quality and data consistency across support and onboarding use cases. Designed and maintained ETL data pipelines and optimized MySQL databases, supporting internal analytics and client-side reporting. Built automated data workflows to extract, transform, and load workspace metrics. Designed and ran SQL queries to assist customers with data management, KPI tracking, and analytics reports, enabling better workspace utilization insights. Technologies Used TypeScript, React, Tailwind CSS, Node.js PHP, MCP, GraphQL, MySQL Docker, Intercom, Jira, Confluence

Introduction

My experience spans software development, data analysis, and IT support roles. I've worked on projects involving LLM-based classification, full-stack development, and cross-functional technical support. I'm particularly skilled in combining technical knowledge with effective communication to deliver solutions that meet real-world needs.

Publications

My research focuses on Natural Language Processing and Large Language Models, particularly in the domain of political stance detection and text classification.
Conference Paper ACL 2025 Student Research Workshop

Exploiting contextual information to improve stance detection in informal political discourse with LLMs

Arman Engin Sucu, Yixiang Zhou, Mario A. Nascimento, Tony Mullen

This study investigates the use of Large Language Models (LLMs) for political stance detection in informal online discourse, where language is often sarcastic, ambiguous, and context-dependent. We explore whether providing contextual information, specifically user profile summaries derived from historical posts, can improve classification accuracy. Our findings show that contextual prompts significantly boost accuracy, with improvements ranging from +17.5% to +38.5%, achieving up to 74% accuracy that surpasses previous approaches.

Projects

Here's a selection of my recent projects showcasing different skills and technologies. Each project demonstrates my approach to problem-solving and technical implementation.
Cafeteria Coffee App
Cafeteria Coffee App

Mobile Application Project

Vancouver, BC

View Project
Streamlit Soccer Platform
Streamlit Soccer Platform

Data Visulalization Project

Vancouver, BC

View Project
LLM-based Political Stance Classification
LLM-based Political Stance Classification

ML&AI Academic Research

Vancouver, BC

View Project

Contact Me

Phone

(+1) 2369653533

Email

raulchou716@gmail.com

Location

🇨🇦 Vancouver, BC, Canada

Stay Connected

Thank you for subscribing!

Something went wrong, please try again.

I respect your privacy and won't share your data.