Hello, my name is
Alfian Bima Prastyo
And I'm a
Fresh Graduate · GPA 3.79 · Open to Work
Alfian Bima Prastyo

About me

I'm Alfian and I'm a

I got into AI when I saw how fast it was changing everything around me and arning became my obsession. That curiosity turned into a real drive to build systems that actually work, not just models that live in notebooks, So I put that obsession to work.

I'm an Informatics Engineering graduate (GPA 3.79) who also completed Bangkit Academy, a 6 month intensive program led by Google, GoTo & Tokopedia. I spent those years building and deploying real AI projects, from an ecommerce customer service agent chatbot to a credit scoring app, with every project shipped live and ready to try right now.

I enjoy the whole process, from messy data to something that actually helps people, and I'm still learning every day, which is exactly what keeps me going.

My Projects

HR Assistant Chatbot

HR Assistant Chatbot

A production grade RAG system that answers HR policy questions using the GitLab Handbook as its knowledge base. Features hybrid search (Vector + BM25 + RRF), bilingual support, streaming responses, conversation memory, and a full monitoring stack with Prometheus and Grafana.

Python FastAPI LangChain Qdrant Hybrid Search Docker Ollama Chainlit

Agentic RAG Customer Service

Agentic RAG Customer Service

An agentic RAG system for e-commerce customer service with 5 specialized agents for FAQ, Product, Order, Promo, and Escalation each with their own knowledge base. Features intent classification, hybrid retrieval (BGE-M3 + BM25 + RRF), and LangSmith tracing, deployed on Hugging Face Spaces.

Python LangGraph FastAPI Qdrant Groq Hybrid Search RAGAS LangSmith

Credit Risk PD Model

Credit Risk PD Model

An end-to-end Probability of Default model trained on Home Credit data. Features rigorous validation including Out-of-Time testing, PSI stability check, fairness analysis by age group, and cutoff policy simulation with stress testing and deployed as an interactive Streamlit app.

Python LightGBM Scikit-learn Pandas Streamlit

Fraud Detection System

Fraud Detection System

A fraud detection model trained on the IEEE-CIS dataset with severe class imbalance. Features custom threshold tuning optimized for cost savings (67% estimated reduction), a full preprocessing pipeline, and deployed with drift monitoring baseline on Hugging Face Spaces.

Python LightGBM Scikit-learn Imbalanced-learn Pandas

Kidney Stone Classification

Kidney Stone Classification
Undergraduate Thesis

A deep learning model for kidney stone detection from ultrasound images using Swin Transformer, achieving 99.57% accuracy and outperforming CNN and Vision Transformer (ViT) baselines. Trained on 9,396 images and published in JATI EMAS journal (Vol. 9, 2025), with a live demo deployed on Hugging Face Spaces.

Python Swin Transformer PyTorch Deep Learning Medical Imaging

My Skills

My core focus is building and deploying arning systems from data preprocessing and model training to real-world deployment. I work mostly in Python and enjoy the full pipeline, from raw data to a working product.

ML & AI
arning Deep Learning Natural Language Processing Computer Vision Retrieval Augmented Generation Large Language Models Agentic AI Feature Engineering Model Evaluation Hyperparameter Tuning
Frameworks & Tools
PyTorch Scikit-learn LangChain LangGraph FastAPI Pandas NumPy Hugging Face Qdrant Docker Chainlit Jupyter Notebook Git
Programming
Python SQL
Deployment
Hugging Face Spaces Streamlit Docker

Experience & Education

Software Engineer Intern
Internship
PT. Salam Pacific Indonesia Lines (SPIL)
Feb 2024 – Jun 2024 Surabaya, Indonesia
  • Conducted user and stakeholder interviews to gather requirements for internal HR applications, including Employee Onboarding, CI/OPI (Continuous Improvement/Operational Process Improvement), and other HR related systems.
  • Designed end-to-end application workflows and system flow diagrams, translating business needs into structured user flows.
  • Created UI/UX designs and interactive prototypes using Figma, iterating based on feedback from users and stakeholders.
  • Developed functional web based prototypes to demonstrate system behavior prior to IT handover.
  • Presented designs and prototypes to users and stakeholders, securing approval before handing over finalized projects to the IT team.
Bussines Analysis Software Development Web Development Figma
Machine Learning Cohort
Education
Bangkit Academy — led by Google, GoTo, Tokopedia & Traveloka
Aug 2023 – Dec 2023 Remote, Indonesia
  • Completed 900+ hours of intensive training in Machine Learning, Python, TensorFlow, and data processing.
  • Collaborated in a cross-functional capstone team (ML, Android, Cloud) to build a Soil Type Detection & Crop Recommendation App.
  • Applied data preprocessing and hyperparameter tuning to enhance model performance.
Python TensorFlow Machine Learning Teamwork
Bachelor of Informatics Engineering
Education
Universitas Pembangunan Nasional Veteran Jawa Timur
Aug 2021 – Dec 2025 Surabaya, Indonesia GPA 3.79 / 4.00
  • Relevant courses: Artificial Intelligence, Machine Learning, Pattern Recognition, Image Processing, Computational Statistics, Database Systems, Algorithms & Data Structures.
  • Thesis: Kidney Stone Classification Using Swin Transformer. implemented and deployed a Swin Transformer model for medical image classification, including data preprocessing, model training, hyperparameter tuning, initially deployed as a Flask web app for thesis defense, later migrated to Hugging Face Spaces for public access.
Swin Transformer Computer Vision Flask PyTorch Medical Imaging

Certifications

Junior Web Programmer
Badan Nasional Sertifikasi Profesi (BNSP)
2024
Artificial Intelligence Fundamentals
IBM SkillsBuild
2026
AI Engineer Professional Certificate
Udemy
2026

Contact me

Let's work together.

I'm currently open to new opportunities, whether it's a full time role or just a conversation about AI and machine learning

Name
Alfian Bima Prastyo
Location
Madiun, Indonesia
Send a message.