SLSY-2026 · REV A · COMPUTER ENGINEERING

STANLEY LIN SHENG YANG

Embedded-systems engineer moving up the stack — from bare-metal C to on-device AI.

GENERAL DESCRIPTION

Stanley Lin is a National University of Singapore Computer Engineering freshman (2026) and Singapore Polytechnic graduate (2024, GPA 3.80/4.00). He builds systems that operate under hard constraints: bare-metal firmware with no OS, on-device AI with no internet, and industrial automation under safety requirements. His work spans PIC18F4550 microcontrollers and IIoT edge deployments at A*STAR ARTC to an offline RAG pipeline for the Republic of Singapore Navy. Outside engineering, he founded Convenient Oasis, an e-commerce venture he ran single-handedly — supplier sourcing, a Shopify storefront, and ACRA business registration.

FEATURES

  • Offline RAG pipeline — 70% baseline accuracy, zero cloud dependency, deployed for RSN
  • Custom-trained YOLOv8 on ~3,000 industrial images for factory collision prevention
  • Bare-metal C firmware on PIC18F4550: Timer0 ISR, DS1307 I²C, sensor fusion
  • IIoT edge computing — 50% latency improvement at A*STAR ARTC
  • Full-stack portfolio spanning Android AR, PHP/MySQL, C++, Python, and Java
Portrait of Stanley Lin Sheng Yang
AIDBUDDY
AI/MLMOBILE

Offline Android clinical-reference app for the Navy Medical Service — on-device Gemma 3 1B RAG chat for Medical Officers, deterministic protocol search for medics, zero connectivity required.

Platform Android — model and vector database entirely on-device
Model Google Gemma 3 (1B parameters) via MediaPipe LLM inference
Base Built on Google's MediaPipe RAG Android sample
Retrieval Hierarchical parent-child chunking — 1000-char parents, five overlapping ~250-char children
ROBOT-HUMAN COLLISION PREVENTION
CVALGORITHMS

Top-down factory collision-prevention system — custom-trained YOLOv8n detects humans and robots through an IP camera, with bounding-box overlap logic raising collision warnings.

Dataset Custom top-down dataset — 1,612 person + 2,132 robot usable instances (2 robot types + human mannequin)
Model YOLOv8n (nano) — custom-trained
Detection Top-down IP camera view; bounding-box overlap triggers collision warning
Role R&D Engineer Intern — A*STAR ARTC
SMART SLEEP INDUCER
EMBEDDED

Bare-metal C sleep-environment automation on PIC18F4550 — dual-RTC timekeeping over I²C, two-sensor activation logic, and a five-stage escalating wake alarm.

MCU PIC18F4550
Toolchain MPLAB X IDE / XC8 C Compiler
Peripherals DS1307 RTC (I²C), 20×4 LCD, 4×4 keypad, PIR sensor, LDR, USB aromatherapy diffuser, buzzer
Context Singapore Polytechnic — MAPP module
PERSONAL WELLNESS ASSISTANCE
FULL-STACK

JavaFX desktop wellness tracker with Harris-Benedict-based daily targets, gamified quiz and badge rewards, and a SOLID-structured OOP design — later migrated from local MySQL to Huawei Cloud RDS for the Huawei Developer Competition APAC 2023.

Platform Desktop — JavaFX with FXML and CSS
Database MySQL 8 — migrated to Huawei Cloud RDS with Elastic IP binding
Targets Harris-Benedict equation for personalized calorie, exercise, and sleep goals
Design MVC + SOLID — separated DB handler, calculator, and validator classes

View all 10 projects →

2.0EXPERIENCE


Organisation Role Period Outcome
Republic of Singapore Navy R&D Engineer (NS) Oct 2024 – Aug 2026 Built AidBuddy — offline on-device RAG clinical decision support for naval medics; scaled at DSTA MedXplore Hackathon
A*STAR ARTC R&D Engineer Intern Sep 2023 – Feb 2024 Developed YOLOv8 robot-human collision prevention; led IIoT edge computing deployment achieving 50% latency improvement
Singapore Polytechnic Research Assistant Mar 2024 – Jul 2024 Managed DL vision model research; built Python monitoring dashboard; authored NLP lab materials; packaged models as single-file executables
Convenient Oasis Founder Late 2024 Sourced suppliers, built the Shopify storefront, and registered the business via ACRA for a US outdoor-hydration brand

3.0SKILLS


  • C, C++, Java, SQL, HTML / CSS Core languages across firmware, backend, and full-stack projects
  • Embedded (bare-metal C) Timer/ISR, I²C peripherals, PIC18F4550 firmware — no OS
  • IoT / IIoT Edge deployments under latency and connectivity constraints
  • Edge Computing, Android On-device inference and native Android development
  • Computer Vision, YOLO (v7, v8) Custom-trained object detection for industrial safety
  • NLP, RAG Pipelines Offline retrieval-augmented generation for clinical queries
  • Git, KNIME, n8n Version control, data workflows, automation pipelines
  • Android Studio Native Android tooling for AR and mobile deployment

4.0CONTACT