Open to Work

Gijin Kim

Backend Developer & AI Engineer
A passionate developer who enjoys simplifying complex world problems and solving them with IT technology. From handling large-scale traffic to developing AI services, I focus on practical problem-solving through various technical challenges.
View Projects Contact Me
About

Hello! 👋

A passionate developer in backend development and AI technology
Gijin Kim Profile Picture
I’m Gijin Kim, a developer who finds fulfillment and happiness in solving complex real-world problems with IT. I focus on building software that delivers value to people, from handling large-scale traffic to developing RAG-based intelligent services. Recently, to expand my ability to solve more problems, I have been studying natural language processing and pursuing related research.
2+
Years Experience
4
Major Projects
400K+
Daily Active Users
4.07/4.5
GPA
Education

🎓 Education

Dankook University

B.S. in Mobile Systems Engineering
Yongin, South Korea
Mar 2020 ~ Current
GPA: 4.07 / 4.5 | Credits Taken: 103/140 (Expected graduation: Sep 2026)
Relevant Coursework: Data Structures, Database, Probability and Statistics, Linear Algebra, Computer Architecture, System Programming, Operating Systems
Experience

💼 Work Experience

Nudge Healthcare (Cashwalk)

Backend Part Leader & Backend Developer
Seoul, South Korea
Apr 2022 – Apr 2024 (2 years 1 month)
Responsible for technical leadership and team management including scrum facilitation, code reviews, API design, and RDB/NoSQL optimization across projects.

Large-Scale Chat Data Processing System Development

  • Designed and developed server architecture to handle large-scale data streams for 400K daily active users (DAU)
  • Developed various messaging features including read receipts, 1-on-1 chat, group chat, and channel talk (simultaneous delivery to 5M+ users)
  • Implemented API design based on Node.js and Nest.JS, and real-time communication using Socket.io
  • Implemented multi-tenant architecture applicable to various services to ensure system scalability
  • Improved data processing performance through RDB/NoSQL (MySQL, DynamoDB, Redis) design and optimization

Global Service Backend and Data Pipeline Development

  • Designed and developed backend systems for global services targeting North America and Europe
  • Built stable architecture considering network latency and data consistency in global environments
  • Maintained and operated features in AWS cloud environment (EC2, RDS, S3, SQS, Lambda, etc.)
  • As part leader, conducted scrum sessions, code reviews, and schedule/task management for the backend team
Projects

🚀 Featured Projects

Projects that solved real problems through various technical challenges

AI-Powered Slack Q&A Bot

May 2025 - Jul 2025 (Personal Project)
Designed and developed a RAG architecture-based Slack bot to build a question-answering system specialized for internal team knowledge. Provides accurate and evidence-based answers to user questions through vector search targeting GitHub codebase and Notion documents.
  • Implemented question classification and routing workflow using LangGraph
  • Vector search system using OpenAI Embedding Model and Pinecone
  • Implemented cron job for automatic embedding updates every hour
  • Designed DB schema and logic supporting multi-tenancy
NestJS TypeScript LangChain LangGraph OpenAI API Pinecone MySQL
GitHub

AI-Based Clothing Recycling Platform

Feb 2025 - Apr 2025 (Personal Project)
Developed a service that automates the clothing recycling sorting process using YOLO models. Improved recycling efficiency with 15-category classification and defect detection features, and built TorchScript optimization and Docker/AWS-based deployment pipeline.
  • Developed clothing image classification and defect detection API using FastAPI
  • Optimized inference performance by converting PyTorch models to TorchScript
  • Docker Hub and AWS Elastic Beanstalk automatic deployment pipeline
  • Built service operation environment using Docker Compose and Nginx
Python FastAPI PyTorch TorchScript Docker AWS Nginx
GitHub

Gym Attendance Motivation App

Feb 2025 - Apr 2025 (Personal Project)
Developed a fitness web/app with gym attendance and social features. Improved the accuracy of gym image verification through prompt engineering using OpenRouter AI and implemented a real-time ranking system using Redis.
  • Gym image verification feature using OpenRouter AI model
  • Real-time ranking and level system using Redis
  • User ranking and score management system
  • User motivation system through social features
NestJS TypeScript MySQL Redis AWS S3 OpenRouter React
GitHub

Food Image-Based Calorie Analysis App

Nov 2024 - Jan 2025 (Personal Project)
Developed an AI API server that analyzes calories and nutritional information from food photos. Fine-tuned YOLOv11 model to detect and classify food objects, building a system that provides accurate nutritional information to users.
  • Fine-tuned YOLOv11 model with 90 food class dataset (mAP 0.85)
  • Real-time image processing pipeline integrated into FastAPI server
  • Stable and scalable server infrastructure based on AWS cloud
  • RESTful API from image upload to nutritional information return
Python FastAPI PyTorch YOLOv11 Docker AWS
GitHub
Tech Stack

🛠️ Skills & Technologies

Technologies acquired through various projects

Programming

TypeScript Python JavaScript Node.js

AI / ML

LangChain LangGraph OpenAI API Pinecone Hugging Face PyTorch YOLO

Backend & DevOps

NestJS FastAPI MySQL PostgreSQL Redis AWS Docker Next.js
Research

🔬 Research Interests

Areas of development through continuous learning and research

RAG & Domain-Specific LLM

Fascinated by research that leverages external information sources to enhance LLM reliability and reduce hallucinations, based on hands-on experience building RAG-based bots. Currently exploring efficient search, indexing, and generation strategies for domain-specific data.

AI Agent

Building on LangGraph-based agent development, passionate about improving interaction quality in conversational AI and advancing autonomous LLM agents capable of handling complex user needs end-to-end.

Contact

📬 Get In Touch

Always open to new opportunities and collaborations

Email

abjin69@gmail.com

GitHub

@abjin

Velog

@abjin

© 2024 Gijin Kim. All rights reserved.