Hi,
I'm Natasha
an AI/ML Engineer
London, UK | (+44) 7380981449

I specialize in AI/ML applications such as fraud detection, chatbot systems, and personalized recommendations, with a focus on building robust, scalable solutions. I also develop landing pages and user-facing tools that integrate seamlessly with AI systems. Proficient in Python, SQL, and cloud platforms, I work end-to-end from model development to deployment.

Outside of work, I enjoy hands-on projects involving IoT (Arduino, Raspberry Pi), 3D printing, and CAD design. In my free time, I unwind through wall climbing and archery.

# ABOUT ME

I'm an MSc student in Applied Computational Science & Engineering at Imperial College London, starting late September 2025. My student visa will be active from late August 2025, so no visa sponsorship is required.

I'm currently seeking part-time internships (up to 20 hours/week) in AI/ML research or engineering or data science/analytics. My daily classes end at 12 PM, so I'm available to come to the office in the afternoons and evenings, with flexibility for remote work earlier in the day if needed.

I have experience in AI/ML engineering, including fraud detection, chatbots, recommendation systems, and graph modeling. Skilled in Python, SQL, and cloud deployment, I build scalable AI solutions from development to deployment and visualization.

# SHOWCASE

# WHAT I BUILD

I focus on practical AI/ML engineering: combining data-driven insights, automation, and scalable deployment. My work spans fraud detection, chatbot systems, and recommendation engines, built using Python, SQL, and cloud infrastructure. Here's a glimpse of my expertise:

1. AI/ML Development & Data Automation

📈 Predictive Analytics & AI Modeling

  • • Models for sales forecasting, demand prediction, and customer segmentation, optimizing e-commerce inventory.

🤖 NLP & AI Chatbots

  • • AI chatbots for resume screening and AI-driven Q&A, enhancing customer support.

🚨 Fraud & Anomaly Detection

  • • Systems to identify fraudulent transactions and provide real-time fraud alerts.

📷 Computer Vision & OCR

  • • Systems for license plate recognition and ID verification, streamlining document processing in financial services.

📑 Data Extraction & Web Scraping

  • • Web scrapers for market research and competitor pricing, integrating insights into dashboards.

2. Dashboards & Landing Pages

📊 Interactive Dashboards & Data Visualization

  • • Business intelligence dashboards (Looker, Power BI, Tableau) for real-time SaaS tracking, KPIs, trading analytics, and more.

🌐 AI-Integrated Web Apps

  • • Development of web apps for AI SaaS platforms (e.g. chatbots, job site matching candidates to job descriptions).
  • • Custom-built dashboard web apps supporting both web and mobile interfaces with UI/UX design using Figma.

🏷️ Branded Landing Pages

  • • Development of branded landing pages for companies and personal portfolios.
  • • Deployment on platforms such as GitHub Pages and Cloudflare, including custom domain configurations.
  • • Designing complex layouts with animations, multi-section, and multi-page formats.
  • • More details available at: github.com/natgluons/web-portfolio-templates

Why Choose Me?

✔️ Delivering end-to-end solutions with attention to detail
✔️ Providing actionable, user-focused insights
✔️ Building scalable and automated AI/ML systems

Let’s work together.

📧 Email: kristynatasha011@gmail.com
💻 Github: github.com/natgluons
📱 WhatsApp: (+62) 8788-658-3513

Highlighted Projects

Retrieval-Augmented Chatbot for Document-Based Q&A

RAG Chatbot

This project is an OpenAI-powered chatbot that uses Retrieval-Augmented Generation (RAG) to enhance responses with relevant information from provided documents.

Key Features
• Deployed using Docker and Kubernetes for scalable service delivery;
• Accessible through a user-friendly web interface;
• Utilizes OpenAI's GPT-3.5 model for natural language processing;
• Built with LangChain to orchestrate LLM workflows efficiently;
• Implements Retrieval-Augmented Generation (RAG) for context-aware responses;
• Features document retrieval capabilities for context-enhanced responses.

Fraud Detection Graph Visualization with D3.js

GNN Fraud

This project uses Graph Neural Networks (GNN) to enhance fraud detection in online gambling and financial transactions in Indonesia. By analyzing transaction networks, it uncovers hidden patterns and detects fraud syndicates more effectively than traditional rule-based methods.

Key Features
• Large-scale graph processing for complex transaction networks;
• Real-time fraud detection capabilities;
• Interactive network visualization tools;
• Node embeddings and K-means clustering for pattern recognition;
• Syndicate scoring system to identify fraudulent user groups.

Youtube Video Recommendation via NLP Keyword Extraction

One of my favorite side projects is a YouTube video recommendation insights tool, where I used the YouTube Data API and NLP to analyze watch history and uncover recommendation patterns.

Key Features
• OAuth 2.0 integration for secure user authentication;
• Transcript analysis and keyword extraction to identify trends;
• Visualization features for better data interpretation;
• Data export capabilities for further analysis.

Customer Goods Data Modeling, Clustering, and Segmentation

Another side project is a Customer Goods Data Modeling project that tackles industrial challenges through predictive modeling for daily sales quantity and customer segmentation.

Key Features
• Utilized PostgreSQL and DBeaver for efficient data ingestion;
• Built interactive dashboards using Tableau Public;
• Developed predictive models in Python using Google Colab;
• Applied time series ARIMA for sales forecasting;
• Used clustering techniques for customer segmentation.

Achievements & Publications

  • 1st Winner Best Paper in ACFE Call for Papers 2024

  • Semifinalist AI Hackathon Bank Indonesia - FEKDI 2024

  • Top 10 Scientific Paper Physics Fair Padjadjaran University

  • Top 10 Scientific Paper Economic Finance Study Club Diponegoro University

PUBLISHED: Propagation Characteristics of Madden Julian Oscillation in the Indonesian Maritime Continent: Case Studies for 2020-2022, Agromet Journal, doi: 10.29244/j.agromet.38.1.1-12PREPRINT / UNDER REVIEW: An Elementary Approach to Predicting Indonesian Monsoon Index: Combining Ann-Arima Hybrid Method and Practical Use

Professional Certifications

  • AML and Data Governance: Risk-Based Mentoring Program for Crimes of Money Laundering and Terrorism Financing in Human Trafficking and Financial Technology Crimes - PPATK

  • Data Science: Certificate of Competencies - Kalbe Nutritionals Data Scientist Project Based Internship Program

  • Full-Stack Development: Certificate of Competencies - BTPN Syariah Fullstack Developer Project Based Internship Program

Coursework Certifications

  • Computer Science for Artificial Intelligence (CS50) - Harvard Online CS50x

  • Google Cloud Professional Machine Learning Engineer Cert Prep - GDG

  • Artificial Intelligence on Microsoft Azure - Microsoft

  • The Full Stack - Meta

  • SQL for Data Science - UC Davis

  • Python for Data Science, AI & Development - IBM

  • E-Learning: Data Science - MySkill

  • Website Development/Backend (Python, Flask) - MySkill

  • Intro to Data Analytics - RevoU

  • Data Programming - Sololearn

  • Data Visualization ShortClass - MySkill

  • Data Analysis - MySkill x Deloitte

  • Power BI Essential Training - LinkedIn Learning

WORK EXPERIENCE

DAnS is an IT solutions provider specializing in software, AI, cloud, and microservices for Telkomsel (Indonesia's leading telecommunications company).

✒️ Fraud Detection System - DigiPOS Telkomsel
• Researched fraud detection approaches using hybrid traditional, deep learning, and semi-supervised models (XGBoost, Random Forest, Isolation Forest, PCA, Neural Networks, Autoencoder) with tri-training methodology and downsampling techniques;

• Designed ML development lifecycle on Google Cloud Vertex AI using AutoML pipeline, clustering algorithms, and fraud pattern detection with Euclidean distance metrics, rule-based labeling, and rule hit detection;

• Architected system infrastructure integrating S3 storage for transaction data, Rule Engine DB for fraud detection rules, Admin Portal for rule management, and automated suspension workflow through Sanction API;

• Developed Fraud Detection System for DigiPOS Telkomsel by implementing the designed ML models and rule-based approach.

✒️ Chatbot Service - GraPARI Telkomsel
• Implemented daily data pipeline scheduling from Google Cloud Storage to BigQuery for automated AI chatbot monitoring;

• Developed Looker dashboards for real-time visualization of chatbot performance metrics, driving data-driven improvements in customer service efficiency;

• Built keyword extraction and topic frequency analysis modules to identify trending customer concerns and optimize NLP model performance.

LinkAja is Indonesia's state-owned e-wallet service, formerly TCASH by Telkomsel.

✒️ Model Development
Achieved 4/4 project completion across model development cycles (1 model per 2-4 sprints), including:

• Implemented PCA and Isolation Forest for anomaly detection in merchant-customer transactions;

• Applied Random Forest and Network Analysis to map illegal online gambling transactions;

• Developed semi-supervised Relational Graph Convolution Network (RGCN) model for collusion risk assessment;

• Created a gradient boosting model that utilizes the Heterogeneous Graph Transformer (HGT) architecture to detect syndicate fraudsters within clustered graphs, contributing to best practices in Anti-Money Laundering (AML).

✒️ Cloud Deployment
Delivered 100% successful execution in model deployment in collaboration with AI/ML engineers, including:

• Utilized GCP cloud automation tools including Cloud Functions and Virtual Machine for model deployment.

✒️ Businesss As Usual (BAU)
Contributed to up to an 11.2% reduction in fraud incidents and saved an average of 95% in potential losses each month through:

• Utilizing device intelligence and computer vision to monitor tampering, cyberattacks, and account takeovers.

• Optimizing SQL queries in BigQuery data marts, reducing query execution times by an average of 180 seconds (saved storage costs).

• Collaborating on real-time data streaming with Apache Kafka and creating Looker dashboards for efficient monitoring.

• Research Associate, AI/ML - FITB Research Grant ITB (academic research)

• Data Scientist Internship - Kalbe Nutritionals (pharmaceutical industry)

• Freelance AI Researcher / NLP Developer - Private Client (hiring services)

• Full-Stack Developer Internship - BTPN Syariah (banking industry)

• Front-End Developer Internship - Core Initiative Studio (software house)

• Data Science Internship - LAPAN (Indonesian National Aeronautics & Space Agency)

• GIS Data Analyst Internship - Garda Caah (Government Disaster Response Program)

TECH STACKS
Programming Languages: Python, C++, Javascript
Libraries/Tools: ML (Scikit-learn, TensorFlow, PyTorch, Keras, XGBoost, OpenCV)
NLP (NLTK, HuggingFace, spaCy)
Visualization (Matplotlib, Seaborn, Pandas, NumPy, Plotly)
Graph Networks (NetworkX, RGCNconv, HGTconv)
Generative AI (GPT-4, Llama, Stable Diffusion/SDXL)
LLM Framework (OpenAI, LangChain), Vertex AI, RAG (Retrieval-Augmented Generation)
Databases: PostgreSQL, BigQuery, MySQL, DBMS (DBeaver)
Development: Code Editor (VS Code, Google Colab), Version Control (Git), Frontend Frameworks (Vue.js, Node.js), Backend Frameworks (Flask, Django)
Deployment: Compute Engine VM, Cloud Functions, Docker, Kubernetes