CV

Computer Science Laboratory, KazNU

Machine Learning Research Engineer

• Learning from physics. Develop physics-informed neural networks and Kolmogorov–Arnold models for computational fluid dynamics, with a focus on two-phase flow in porous media.
• Training and inverse modelling. Develop and compare training methods for scientific ML. Study how optimisation, competing objectives, and noisy measurements affect predictions and the recovery of physical parameters.
• Research proposals and grants. Develop research methods and write grant proposals to explore new directions in machine learning and its applications.
• Quantum machine learning. Research quantum machine learning methods for optimisation and computational fluid dynamics.
• Modelling academic success. Built iLearn to identify academic support needs from 26,000+ student records. Deployed at two public universities; the research included collaboration with King’s College London.

National Engineering Academy of the Republic of Kazakhstan

Machine Learning Research Engineer

Built models to predict oil recovery and fluid properties. Worked on GPU acceleration, training across multiple machines, and faster inference with high-performance computing engineers.

Al-Farabi Kazakh National University

AI & Machine Learning Instructor

Designed and taught a four-week course, from first principles to building and evaluating models. Also teach and assist at international summer and winter schools, and volunteer in English-language teaching.