I am Afrasiyab Khalili, a Research Associate with a background in data and software engineering, and a bit of AI. Previously based in Tallinn, Estonia, I mainly worked on building scalable marketing data pipelines, cloud-native solutions, and non-prod machine learning applications. My work focuses on optimizing data infrastructure to drive business insights and efficiency.

Professional Background

I was a Data Engineer at Bally’s Interactive in Tallinn, Estonia (October 2022 - Present), where we (multiple data teams, I was part of marketing) built real‑time data platform powering systematic operations, advanced AI/ML capabilities, real‑time decision‑making, marketing optimisation, and personalised player experiences. The main project was the migration of legacy IBM data warehouses to cloud-native lakehouse - Databricks, AWS. This initiative is expected to reduce infrastructure costs by half. I also enhance team tooling with automation, participate in on-call shifts, contribute to data architecture discussions, and design end-to-end pipelines following the Medallion architecture. My toolkit includes Apache Spark/PySpark, Apache Airflow, AWS, Google Cloud Platform, SQL, Python, Docker, and more.

Previously, I served as a Data Engineer at Solita in Tallinn (September 2021 - September 2022), developing ETL solutions with Apache Airflow, automating data migrations, and supporting datawarehouse design and transformations/analysis in Redshift.

I also worked as a Software Engineer at Sigma Technical Services LLC in Baku (September 2020 - August 2021), developing system with 2D LIDAR on Raspberry Pi, visualizing real-time data with PyQt, and implementing object tracking using clustering algorithms and motors in static/dynamic environment.

Education

Master of Science in Computer Systems Engineering, Tallinn University of Technology (TalTech), Tallinn, Estonia (September 2021 - 2024), GPA: 4.278. Received tuition fee waiver (2 years) and excellence scholarships (twice). Honored with an invitation to the Presidential Rose Garden reception from the President of Estonia and Minister of Education. Bachelor of Science in Computer Science, University of Strasbourg/Azerbaijan State Oil and Industry University, Baku, Azerbaijan (September 2016 - June 2020), GPA: B+. Relevant coursework: Data Structures and Algorithms, Parallel Programming, Signal Processing, Computer Architecture, Operating Systems, Networks, Combinatorics, Linear Algebra, Quantum Mechanics. Received government scholarships (tuition fee waiver + monthly stipendium for 4 years) and selected for Thales Group certification courses (only top 10 students were chosen).

Projects

From Pixels to Patterns: Automated Classification of Fish Swarms in Underwater Videos (Funded by BfG): Developed an explainable machine learning system for classifying fish behaviors in fishways, reducing manual observation and costs. Golf Course Management Subsystem: Built conceptual data models, CRUD matrices, and database implementations using Enterprise Architect, incorporating business rules. ANN Library in C: Implemented a neural network with ReLU and Sigmoid activations for hidden and output layers. LIDAR System for Object Detection and Tracking: Created a security application on Raspberry Pi using Python/C, with real-time data visualization and clustering. Predicting Heart Disease Risk: Trained MLP models on the Cleveland Heart Disease dataset using Python/Java. Design of Interlocking System for Metro Station (Thales Project): Visualized and simulated metro interlocking systems in Python. Classification using Decision Tree and K-means++: Implemented classification and clustering algorithms in Python/Java. Panorama: 3D to 2D Image Stitching: Merged 360-degree photos into a single BMP using C, with shift detection and resizing. Image Processing - Strip Extraction: Extracted image strips in C for archaeological applications.

Skills and Certifications

Programming Languages: Python, SQL, Java, C, Shell. Technologies: AWS, Redshift, Airflow, Linux/Ubuntu, Weka, Git, LaTeX, JIRA, MIRO, Bitbucket, Agile, Apache Spark/PySpark, Apache Kafka, Docker, Continuous Integration/Deployment (CI/CD). Certifications:

Apache Kafka - Administration & Development AWS Certified Cloud Practitioner Databricks Lakehouse Fundamentals Apache Airflow Astronomer Certification (DAG Authoring & Fundamentals) What is Data Science? (Coursera, IBM) Neural Networks and Deep Learning (Coursera, DeepLearning.AI) Automation and Computer Technologies in Transport (THALES Group)

Languages

Azerbaijani (Native) Turkish (Advanced) English (Advanced) French (Intermediate)