Kallibek Kazbekov

- Architect and lead scalable Snowflake-based data platforms and automated pipelines to support analytics and AI initiatives; - Oversee data migrations, modeling, and governance to ensure performance, quality, and security; - Optimize Snowflake environments for cost, speed, and reliability through proactive monitoring and tuning; - Collaborate with stakeholders and mentor engineers to drive best practices and continuous improvement in data engineering.

- Designed and optimized BigQuery data marts, reducing execution times from minutes to seconds, enabling efficient analytics and reporting - Built efficient ETL data pipelines with AWS and GCP, decreasing pipeline cost by 30%. - Tech leading a dev project that involves full-stack development and dashboarding - Automated data quality reporting for data marts, enhancing monitoring and reducing manual effort - Conducted technical interviews for data engineering roles

- Designed cloud data architectures using AWS, Azure, and GCP for different client projects, reducing latency by 40% and enhancing scalability. - Engineered data pipelines with Airflow and dbt, boosting processing efficiency by 35% across diverse engagements. - Automated infrastructure with Terraform, cutting deployment times by 50% on various client projects. - Optimized analytics on select projects with Databricks, improving processing performance by 25%. - Developed data warehousing solutions using Snowflake on separate client initiatives, enhancing query performance and data accessibility.

- Optimized Hive storage and Spark query execution, cutting data retrieval time by 25% - Designed and developed data marts - Deployed and maintained multiple ML models in production - Built efficient data pipelines using Oozie, reducing pipeline failures by 20% - Conducted technical interviews for data engineering roles

- Collaborated with a data team of nine members to develop a tax monitoring tool for the Tax Authority of Uzbekistan using Hadoop, Kafka, Spark, Hive, Postgresql, Clickhouse, and Airflow. - Designed and implemented scalable and reliable ETL pipelines to process real-time and batch data from various sources across the country, such as receipts, invoices, money transfers, and other tax-related entities. - Performed unit testing and quality assurance on the ETL jobs using Spark and ensured data accuracy and integrity. - Optimized the data lake and serving layer performance by applying best practices and tuning techniques for Hadoop, Kafka, and Postgresql. - Contributed to the successful launch and deployment of the tax monitoring tool, which resulted in improved tax compliance, increased revenue collection, and enhanced transparency and accountability for the Tax Authority of Uzbekistan.

- Updated and maintained GIS database with current and relevant spatial information, ensuring data integrity and accessibility. - Analyzed geospatial data using ArcGIS, Python, and SQL to support decision-making and planning for various projects and clients. - Developed spatial ETL workflows to automate data conversion, transformation, and validation processes, resulting in improved efficiency and accuracy. - Integrated GIS in construction projects to provide spatial analysis, visualization, and reporting capabilities, enhancing project management and delivery. - Developed data models to represent spatial relationships, attributes, and constraints, facilitating data analysis and manipulation. - Produced web maps using ArcGIS Online and Web AppBuilder to disseminate spatial information and insights to internal and external stakeholders. - Monitored data quality using various tools and methods, such as topology, metadata, and error reporting, to identify and resolve data issues and inconsistencies. - Conducted GIS/GPS trainings for staff and partners to increase their knowledge and skills in using spatial technologies and applications.

- Gathered hydrological data from various sources, including government databases, remote sensing technology, and historical records; - Developed and fine-tuned machine learning models, such as regression analysis, neural networks, and ensemble methods, to predict stream flow patterns; - Implemented feature engineering techniques to improve model performance and accuracy; - Utilized programming languages such as Python and R for coding and implementing machine learning algorithms; - Employed libraries and frameworks like TensorFlow, Scikit-learn, and Pandas for efficient model building and evaluation; - Created visualizations and dashboards to present model results and insights using tools like Matplotlib, Seaborn, and Tableau.

- Analyzed and processed large financial datasets to identify trends, optimize reporting, and enhance decision-making, improving operational efficiency by 15%. - Developed SQL queries and Python scripts to automate data extraction, reducing manual reporting time by 30%. - Maintained and optimized Oracle databases, ensuring data integrity and reliability for risk assessment models. - Built interactive dashboards in Excel, providing real-time insights for senior management, leading to more informed financial strategies. - Collaborated with cross-functional teams to refine data models and reporting structures, streamlining internal analytics workflows.

- Assisted the socio-technical survey on Water User Association in Central Asia (Kyrgyzstan, Tajikistan and Uzbekistan); - Entered survey data into the SPSS statistical software; - Assisted with the analysis of the data.

MS Thesis: "Streamflow Prediction using Machine Learning in the Aral Sea Basin (Central Asia)". Courses: - Cpt_S 570 Machine Learning; - Cpt_S 575 Data Science; - CE 543 Inverse Problems; - CE 564 Numerical Methods; - CE 456 Sustainable Development in Water Resources; - CE 514 Environmental Biophysics; - CE 560 Advanced Hydrology; - CE 550 Hydroclimatology.

Courses: - Academic writing; - Academic reading; - Academic communication.