Skip to content
AS

Amina Shaikym

@Amina-shaikymConnected with DSML. This person's Telegram account has been confirmed through DSML Kazakhstan.

AI/ML Engineer

I'm a Data Engineer and ML researcher, still learning and growing in the field. I try to be useful with the technologies I work with and build things that genuinely benefit people.

Open to

Research collaborationStartup collaborationJoining competitions & hackathonsProject collaborationPaper discussions

About

Right now I'm a Visiting Scholar at UPenn, and I previously completed a Data Engineering program at EPAM Systems, where I got to combine hands-on infrastructure work with applied ML research. Since 2023, I've also been working as a TA and Lecturer at SDU University, teaching programming courses and conducting research.

Career

Experience

Lecturer

SDU University

Sep 2025 — Aug 2026

• Teaching undergraduate courses in Algorithms and Programming and Personal Development in Computer Science for over 100 students, fostering analytical and professional growth. • Supervise independent study projects and provide research mentorship, guiding students in data analysis and applied machine learning.

Assistant Instructor

SDU University

Sep 2022 — Aug 2025

• Delivered practice lessons in Fundamentals of Programming 1 & 2, ICT, and Python Programming to over 600 students, improving pass rates and technical proficiency. • Contributed to the Young Researcher Council, initiating and coordinating faculty-student research projects that promoted applied computing and interdisciplinary collaboration. • Provided academic advising for 50 freshmen cohorts, supporting course selection, time-management strategies, and transition to university study.

Data Engineering Intern

EPAM Systems

Nov 2025 — Jun 2026

• Built an end-to-end medallion pipeline on Azure Databricks, ingesting five legacy Parquet sources (97M orders, 957K customers) into Delta tables and exposing aggregated Gold tables for analytics. • Engineered a Spark-based validation layer that deduplicated, normalized, and standardized geographic/address data, routing invalid records to dead-letter tables while tracking rejection volumes and reasons.

Visiting Scholar

University of Pennsylvania

Jun 2026 — Present

• Developed a multi-class affect detection pipeline classifying student emotional states from a dataset of 243 students with 400+ behavioral and keystroke features. • Built a leakage-safe evaluation framework using student-level nested GroupKFold cross-validation, benchmarking Logistic Regression, Random Forest, and XGBoost across feature ablations. • Applied targeted preprocessing (selective log1p scaling, correlation pruning) and feature selection methods (filter/wrapper/embedded) to manage a high-dimensional feature space.

Education

M.Sc in Computer Science

SDU University

Thesis: Title: "Personalized Job Recommendation System" • Developed a hybrid recommender integrating content-based filtering, collaborative filtering, and NLP feature extraction to match computer science students with relevant career opportunities. • Implemented data preprocessing pipelines (Pandas, NumPy) and vectorized profiles with TF-IDF and cosine similarity, achieving a 22% increase in precision compared to baseline models. Coursework: Research Tools and Methods, Data Collection and Wrangling, Machine Learning, Natural Language Processing, Deep Learning, and Mathematics for Data Science

Selected projects

Personalized Job Recommendation System

• Developed a hybrid recommender integrating content-based filtering, collaborative filtering, and NLP feature extraction to match computer science students with relevant career opportunities. • Published papers in Scopus journal.

Achievements

Research Scholarship Award

The Shakhmardan Yessenov Foundation · 2026

The Shakhmardan Yessenov Foundation runs an annual grant competition, awarding 10 grants to active research associates who wish to undertake a research internship at a leading laboratory abroad. Through this scholarship, I joined the University of Pennsylvania as a Visiting Scholar.

Skills

PythonTensorFlowPyTorchScikit-learnPandasNumPyMatplotlibSparkDatabricksDelta LakeHadoopHiveKafkaAzure (Data FactorySynapseHDInsight)ParquetSQL