Skip to content
View szeyu's full-sized avatar
:electron:
Upskilling Myself
:electron:
Upskilling Myself

Highlights

  • Pro

Block or report szeyu

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
szeyu/README.md

Sim Sze Yu Banner

Sim Sze Yu

AI-native builder working across data engineering, finance systems, and agentic workflows.

I build practical systems with AI agents, financial data, cloud data pipelines, and fast product prototypes.

Portfolio LinkedIn Medium Email

GitHub Kaggle Instagram Profile Views


πŸ‘€ About Me

I am a Computer Science student at Universiti Malaya who enjoys building systems at the intersection of AI, finance, and data engineering.

Instead of only building isolated apps, I am interested in designing workflows, infrastructure, and tools that help people:

  • reason better with data
  • automate repetitive work
  • make better financial and operational decisions
  • turn messy ideas into usable products

My work usually falls into four areas:

πŸ€– AI Agents

LLM workflows, RAG, MCP tools, orchestration, automation

πŸ“ˆ Finance Systems

Market data, backtesting, personal finance, investment research

πŸ”§ Data Engineering

ETL pipelines, orchestration, data quality, cloud workflows

πŸš€ Product Prototypes

Hackathon MVPs, AI web apps, fintech tools, developer utilities


🎯 Current Focus

Area What I am exploring
πŸ€– Agentic AI LLM orchestration, MCP, Claude Code workflows, RAG, tool-calling agents
πŸ“Š Quant / Finance Autonomous alpha discovery, backtesting, market data pipelines, investment decision support
πŸ”© Data Engineering Data pipelines, orchestration, CI/CD, data quality, warehouse automation
⚑ Product Building Fast MVP development, AI-assisted engineering, workflow-first software design

πŸ› οΈ Tech Stack

Tech Stack


πŸ“Œ Selected Work

Project Area What it shows
Vibe Quant Quant / AI Autonomous alpha discovery using LLM agents, vector memory, and backtesting workflows.
UM Datathon Bitcoin Strategy Quant / Data Bitcoin algorithmic trading strategy research and backtesting.

πŸ’Ό Experience

Role Organization Period Focus
Data Engineering Intern Ryt Bank / YTL Digital Bank Jul 2025 – Jan 2026 Data pipelines, orchestration, cloud data infrastructure
Data Intern YTL AI Labs Apr 2025 – Jun 2025 Built web crawling scripts to collect training data; used LLMs to generate synthetic data for ILMU, Malaysia's homegrown LLM
AI Fullstack Developer Intern EmbeddedLLM Jul 2024 – Sep 2024 Built full-stack AI applications with LLM backends; developed REST APIs, integrated third-party LLM providers, and shipped customer-facing web interfaces for LLM-powered features
Software Engineer Intern Techtics Solution Sdn Bhd Apr 2024 – Jun 2024 Developed blockchain-based features and smart contract integrations; contributed to backend development and internal tooling

πŸ† Hackathon Highlights

πŸ† View all hackathon highlights (18 events)
Achievement Hackathon Project Link
πŸ₯‡ Top 10 Finalist KitaHack 2026 Personalised financial planner that visualises wealth growth Repository
πŸŽ–οΈ Consolation Prize UKM Data Challenge 2025 Data insight on population and water stress across Malaysian states Repository
πŸ₯‰ 2nd Runner Up Alibaba Cloud Malaysia AI Hackathon 2025 FundSight AI: grant recommendation system for Malaysian SMEs Repository
πŸ₯ˆ 1st Runner Up KitaHack 2025 Medimate: healthcare management assistant Repository
πŸŽ–οΈ Consolation Prize VHack 2025 Medimate: healthcare management assistant Repository
πŸ₯ˆ 1st Runner Up UMHackathon 2025 AmanahBlock: Shariah-compliant AI and blockchain donation platform Repository
🀝 Participant Deriv Hack 2025 AI agent for dispute resolution using OCR and cross-checking tools Repository
πŸ† Champion UM Datathon 2024 Bitcoin quant algorithmic trading strategy Repository
πŸ₯‡ Top 10 Finalist Deriv Hack 2024 AI eKYC project Repository
πŸ₯‡ Top 15 Finalist Setel Hack 2024 AI-powered chatbot for retail Repository
🀝 Participant GodamLah 2024 Enhanced AI eKYC project Repository
🀝 Participant PayHack 2024 FinScope project Pitch Deck
🀝 Participant MYHackathon24 Cohort 1 StackOverflow-like website for public complaints Repository
🀝 Participant MYHackathon24 Cohort 2 AI listener that flags suspicious phone calls Drive Folder
🀝 Participant IHAX 2024 Marketplace of PDF embeddings for learning materials Repository
🀝 Participant UMHackathon 2024 Chat RAG with personal finance data Repository
🀝 Participant KitaHack 2024 Daily RUOK: daily mental health screening Repository
🀝 Participant 1st Day Hack 2022 Navigation support concept for visually impaired users Repository

πŸ“Š GitHub Stats

GitHub Stats GitHub Streak
Top Languages

πŸ–₯️ Environment

Sim Sze Yu OS & Environment


✍️ Writing & Connect

I write about AI, finance, software engineering, and building useful systems. Open to conversations around AI agents, data engineering, finance systems, quant research tooling, hackathons, and AI-assisted software engineering.

Medium LinkedIn Email Portfolio


β˜• Support

β˜• Love my work?

If my projects, writing, or open-source work helped you, you can support me on Ko-fi.

Support Me on Ko-fi

Pinned Loading

  1. Awsome-Android-Code-Template Awsome-Android-Code-Template Public

    A collection of commonly used Android templates to accelerate development workflow. Each template is designed to be modular and easily integrated into your Android projects.

    Java 10

  2. streamlit-authentication-template streamlit-authentication-template Public template

    A streamlit template which is able to handle the login and store users data in database powered by PostgreSQL. It also handles the navigation among login state, signup state and app state with auth…

    Python 17 3

  3. WIX1002-Collections WIX1002-Collections Public

    A collections of Tutorial, Lab and Past Year Questions with Answer for WIX1002 Fundamental of Programming (FOP)

    Java 9

  4. WIA1002-Collections WIA1002-Collections Public

    A collections of tutorials, labs and past year questions and answers of WIA1002 Data Structure course

    Java 1

  5. Agent-Dev-PydanticAI Agent-Dev-PydanticAI Public

    A structured syllabus for an Agent Development Course using Pydantic AI

    Jupyter Notebook 4 1

  6. facevector-engine facevector-engine Public

    FaceVector Engine - Face recognition and vector similarity search API using ArcFace embeddings, RetinaFace detection, and PostgreSQL pgvector

    TypeScript 3 1