Discover My Journey

"I've always been that curious person intrested in documentaries and always wondering how our daily tech gadgets work. I mean, what's behind the screen, right?
Diving into it, I discovered the beautiful complex reasoning that ties everything together. But really, it was my need to figure out the 'how' and 'why' of technology that got me started into the coding world. Below is an overview of my experience in tech."

Applications Engineer 2024 – 2026

Designed and delivered internal automation and reporting solutions using Python, SQL, ETL, and Power BI. Focused on process standardisation, data reliability, and reducing manual finance workflow effort.

AI & Automation Engineer 2026 – Present

Applying AI and automation to accelerate development, debugging, and internal operations. Working across React, Flask, SQL, and Python to deliver scalable business tools and improved team productivity.

Fluent in English, Spanish and Albanian, aiding in diverse communication and collaboration.
Adept at staying updated with the latest tech trends and innovations.
Driven by a passion for innovation, I am committed to continuous growth and learning in the ever-evolving world of technology.

"The above experiences have helped me build a strong foundation in software, but also in problem-solving, critical thinking, and continuous learning. My curiosity extends beyond technology. I'm passionate about connecting with people, socializing, and exploring the variety of diverse cultures. Understanding the challenges others face and fostering the power of teamwork are at the heart of my values. I thrive in environments that champion collaboration, innovation, and mutual understanding."

Interested in My Credentials?

Discover my professional journey, qualifications, and the expertise I bring to the table.

Download My CV

Skills

Machine Learning & AI

Machine Learning is one of my core strengths, supported by my Professional Certificate in AI and ML from Imperial College Business School. I have hands-on experience with model evaluation, hyperparameter tuning, decision trees, Bayesian optimization, and deep learning, including CNNs. I also explore Transformers, OpenAI API, and RAG solutions using tools such as scikit-learn, PyTorch, TensorFlow, and LangChain.

Computer Science Foundations

Built on a strong Computer Science foundation, including algorithms, data structures, probability, and linear algebra, all of which support my work in machine learning and data systems.

Python, APIs & Automation

Python is my main language for data processing, automation, and internal tooling. In my current role, I use it to build ETL pipelines, clean and transform data, automate workflows, and connect systems. I also develop Flask APIs and work with Pandas, PySpark, and object-oriented design to create reliable, maintainable solutions. I am also a Certified Python Developer through the Python Institute.

SQL, ETL & Data Engineering

SQL is a core part of my daily work. I build and optimise queries, automate reporting, manage stored procedures, and support reliable data flows across systems. I also work with the SQL Server stack, including SSIS for ETL and SSRS for reporting, helping improve data quality, process speed, and operational efficiency.

BI, Analytics & Visualisation

I use Power BI to build dashboards, reports, and KPI tracking solutions that support business decisions. For deeper analysis, I also use Python libraries such as Matplotlib and Seaborn to explore trends, validate findings, and communicate insights clearly.

Tools & Platforms

Alongside Python and SQL, I work with Git, GitHub, PowerShell, Power Apps, Power Automate, and Microsoft Azure. These tools help me automate processes, support internal applications, and deliver practical business solutions.

Curious & Analytical

Driven to learn quickly, explore new tools, and solve problems with structure.

Can-Do Attitude

Comfortable taking ownership, improving processes, and learning by doing.

Problem-Solving

Focused on building practical solutions that reduce manual effort and improve efficiency.

Teamwork

Enjoy working with others, sharing knowledge, and contributing to team goals.

Portfolio

All Work
Data & Machine Learning
Visualization
Full-Stack
Front-End

60 Second Care

Gemini API | JavaScript | PHP

Built a responsive web integration using Gemini API with server-side PHP and JavaScript front-end.

Bayesian Optimisation

Pandas | Numpy | Skitlearn

Built a Bayesian optimisation workflow to tune black-box functions with Gaussian Processes.

Churn Prediction

Spark | Pandas | PyTorch | Skitlearn

Developed an end-to-end churn model with feature engineering, analysis, and prediction.

MoM Portfolio Overview

DAX | PowerQuery | PowerBI

Built a Power BI dashboard to track month-over-month portfolio movement and KPIs.

Python Scrapper

Python | Pandas | Request | OOP

Automated real estate data collection with Python, cutting down manual research time.

Investment Performance

DAX | PowerQuery | PowerBI

Designed an interactive dashboard to monitor returns across investment account categories.

SKBIL

HTML | CSS | JS | PHP

Built and launched a car trading website independently for a real client.

Illyrian Grooming Studio

HTML | CSS | JS | PHP

Designed and launched a business website independently for a real client.

Company Directory

JS | PHP | MySQL

Built a CRUD web app for managing personnel records in a structured MySQL database.

E-Commerce Store

React | Node | Express | Postgres|

Built a full-stack e-commerce app with authentication, sessions, and cart functionality.

📌 Project Overview: Developed for a Bayesian Optimisation (BO) competition to optimise eight unknown black-box functions across domains such as contamination detection, drug discovery, and hyperparameter tuning. Functions were high-cost to evaluate — queries allowed only every few days — simulating real-world constraints.

🔍 Problem Breakdown

Each function reflected a specific industrial/scientific task:

Function 1 – 2D: Radiation Source Detection
Function 2 – 2D: Noisy ML Simulator
Function 3 – 3D: Drug Discovery
Function 4 – 4D: Inaccurate Business Model
Function 5 – 4D: Chemical Yield
Function 6 – 5D: Cake Recipe Optimisation
Function 7 – 6D: ML Hyperparameter Tuning
Function 8 – 8D: High-Dim Black-Box Search

Initial observations were provided in .npy format to seed Gaussian Process (GP) fitting.

📚 Research-Informed Strategy

Inspired by state-of-the-art work:

HEBO (Huawei, NeurIPS 2020)
Warped GPs (Snelson & Rasmussen, NIPS 2003)
Acquisition Blending (arXiv:2206.03301)

These guided our approach to transformations, noise handling, kernel structure, and acquisition strategy blending (EI + PI + UCB via NSGA-II).

🛠️ Tools & Technologies

Language: Python 3.10+
Libraries: numpy, scikit-learn, scipy, matplotlib, pymoo
GP Kernels: RBF, Matern, RationalQuadratic, Constant, White
Optimisation: NSGA-II (pymoo) for acquisition mixing
Exploration: ε-greedy, dynamic bound restriction
Diagnostics: PCA, Random Forest feature importance

⚙️ End-to-End Pipeline

Problem Understanding: Defined bounds from context and units
EDA: Outlier checks, noise estimation, distribution plots
Transformations: Yeo–Johnson, Box–Cox (output), Kumaraswamy or MinMax (input)
Kernel Design: RBF for smoothness, Matern for nonlinearity, White for noise
GP Structure: Constant × (RBF + Matern) + White
Acquisition: EI + PI + UCB (MACE routine)
Iteration Loop: Fit → Optimise → Submit → Update → Log mean/variance
Visualisation: PCA to reduce and track GP uncertainty & decisions

🧠 Key Insights

Reusable pipeline enabled fast, consistent strategy testing
Dynamic bound shrinking & feature filtering helped in high-D settings
Warping + WhiteKernel tuning improved generalisation under noise
Transformation choices heavily affected GP smoothness & acquisition
NSGA-II acquisition mixing improved late-stage exploration vs exploitation

✅ Results

Delivered strong results across the board, with top performance in Function 6. Applied advanced BO techniques in a realistic, high-cost query environment.

GitHub

Summary

GitHub

Summary

Road Accidents PowerBI 📚🗂️🧮

This project was focused on gaining practical knowledge of Power BI. I cleaned data, replaced faulty values, and created a Calendar Table connected to accident records. I also built dynamic visualizations and used measures to create an interactive dashboard.

View on GitHub

Global Sales PowerBI (Sales Performance Dashboard) 📈🔍📉

Using a Super-Store dataset, I performed an Exploratory Data Analysis (EDA) and created KPIs using DAX in Power BI. The final output was an interactive dashboard meeting the stakeholders' requirements.

View on GitHub

Correlation Python 🔍📉🔢

My aim in this project was to learn and practice correlation. I cleaned missing data, handled duplicates, and visualized correlations using scatterplots. Additionally, I created a heatmap for the correlation matrix and studied correlation significance using the t-test, specifically focusing on t-values and p-values.

View on GitHub

Turkish Elections Result Analysis 📊💻📈

In this project, I collected election data, merged it with GeoJSON, and created an interactive map using D3 to visualize election results.

View on GitHub

Technologies and Tools

PowerBI
Python
SQL
Pandas, NumPy
Matplotlib, Seaborn
Sqlalchemy
SciPy
JavaScript (D3)

View all Projects on GitHub

Contact Me

Regardless of the time, I am always available to discuss, collaborate, and connect.
Do not hesitate to reach out.