Skip to content
DSML.KZ

Balgabek Zhaksylyk

@balgabek-zhaksylyk

Junior Data Engineer | ETL, SQL, and Data Platforms

I’ve been building things across data engineering and machine learning, from Airflow pipelines to a BERT project about mental health posts. Lately I’ve been working with financial reporting data and StarRocks.

Career

Experience: 1 years

Experience

Junior Data Engineer (BI Financial Reporting)

Kaspi.kz

A major Kazakhstan fintech and e-commerce group offering banking, payments, marketplace, and digital services to consumers and businesses.

Dec 2025 — Present

Worked on financial reporting migration to StarRocks, SQL optimization, and enterprise ETL and Oracle data workflows.

• Worked on migration of financial reporting systems to StarRocks • Optimized complex SQL queries improving reporting performance • Developed and maintained ETL pipelines for enterprise data workflows • Supported Oracle-based data extraction and validation processes

ML Engineer Intern

Biometric Vision

Aug 2025 — Nov 2025

Built biometric computer vision models and processed 50,000+ images, improving accuracy by 8% and reducing inference latency by 15%.

• Developed computer vision models for biometric recognition systems • Processed and cleaned datasets of 50,000+ images • Improved model accuracy by 8% and reduced inference latency by 15%

Education

B.Sc., Computer Science and Software Engineering

Kazakh-British Technical University

2026

Selected projects

MoodInsight (Bachelor Thesis)

Built a full-stack AI platform for mental health text classification. Fine-tuned BERT on 53,000+ posts, achieving 90% accuracy. Developed REST APIs in Go with JWT authentication and asynchronous workers.

Airflow ETL Pipeline

Built automated ETL pipelines using Apache Airflow and containerized workflows with Docker and PostgreSQL integration.

Apartment Price Prediction (Krisha.kz)

Built an ML model for real estate price prediction in Almaty, with feature engineering and model optimization using XGBoost.

Skills

PythonGoSQLJavaETLData WarehousingSQL OptimizationPostgreSQLOracleMySQLGreenplumStarRocksDockerAirflowKafkaGitPyTorchTensorFlowScikit-learnXGBoost