M.Sc. Student • ML / Data Science • Koblenz, Germany

Hi, I’m Kishan Sheladiya.
I build ML systems and data-driven products.

Machine Learning Developer with 1.5+ years of experience in ML/AI, analytics, and production-ready Python solutions. Currently working on time series classification using Optimal Transport with GPU acceleration.

PythonPyTorchCUDASQLFastAPIAWS
Kishan Sheladiya
1.5+ yrs
Experience
ML/AI
Focus
M.Sc.
Current

About Me

I am a Machine Learning Developer and Master’s student in Mathematical Modelling, Simulation and Optimization at Universität Koblenz, Germany. I have over 1.5 years of experience working on machine learning, data analytics, and AI-driven systems.

My work focuses on building production-ready ML solutions — from data pipelines and exploratory analysis to model development, optimization, and deployment. I enjoy combining strong mathematical foundations with practical engineering to solve real-world problems.

Currently, my master’s thesis explores time series classification using Optimal Transport methods, leveraging GPU acceleration (PyTorch + CUDA) to achieve significant performance gains over classical techniques.

Current Degree
M.Sc. Mathematical Modelling
University
Universität Koblenz
Experience
1.5+ Years
Primary Focus
Machine Learning & AI
Thesis Area
Time Series & Optimal Transport
Location
Koblenz, Germany

Education

Academic background focused on mathematical modelling, ML/AI, and data-driven methods.

Master of Mathematical Modelling, Simulation and Optimization

Universität Koblenz • Germany

Oct 2022 – Present
  • Machine Learning and Data Mining, Artificial Intelligence, Optimization, Data Science, Big Data.
Current

B.Tech. Mechanical Engineering

Vellore Institute of Technology • Vellore, India

Jul 2018 – May 2022
  • Python, Advanced Engineering Mathematics, Statistics, Operations Research, Data Analytics.
Completed

Experience

Internships focused on ML engineering, analytics, automation, and turning data into production-ready insights.

Intern Machine Learning Developer

Shree Ram AgricultureGujarat, India

Jan 2022 – Jun 2022
  • Contributed to machine learning framework development, AI integration, and automation programming.
  • Designed and executed reliable, maintainable, bug-free code modules for multiple applications.
  • Worked on deep learning and mathematical aspects of AI; used AWS for parts of the workflow.
Machine LearningAI IntegrationAutomationDeep LearningAWS
Most recent internship

Data Analyst Intern

Kautilyum IT ServicesGujarat, India

Apr 2021 – Sep 2021
  • Managed databases, assessed data quality, and identified patterns/trends to improve data flow.
  • Converted complex data into actionable insights for stakeholders.
  • Built visualization modules and dashboards using Python and Power BI.
PythonSQLPower BIDashboardsData Quality
Earlier internship

Master Thesis

Featured research project combining Optimal Transport, GPU acceleration, and real-world time-series classification.

May 2025 – Oct 2025

Time Series Classification by Optimal Transport Method

Universität Koblenz

Featured

Built a GPU-accelerated Optimal Transport Warping (OTW) approach for efficient, accurate time-series classification and benchmarking against DTW on UCR datasets.

  • Implemented a GPU-accelerated OTW model in Python (PyTorch) with CUDA for efficient time-series classification.
  • Benchmarked OTW vs. Dynamic Time Warping (DTW) on 7 UCR datasets, achieving higher accuracy in structurally complex domains.
  • Applied machine learning, optimization, AI, and statistical techniques on real-world time-series (medical, energy, traffic).
  • Developed a reproducible pipeline for experiments and benchmarking, linking advanced mathematical methods with practical applications.
PythonPyTorchCUDAOptimal TransportTime SeriesBenchmarking

Key Results

Speedup
Up to 70× faster
Error
Up to 60% lower
Datasets
7 UCR datasets
Metrics are reported from thesis benchmarking (OTW vs. DTW).

Projects

A selection of personal projects focused on ML, ETL, analytics, and real-world evaluation.

View GitHub

Book Recommendation System

Machine Learning • Personal ProjectJan 2025 – Mar 2025

Featured

Built an end-to-end recommendation workflow with ETL, EDA, feature work, and evaluation for better ranking and personalization.

  • Performed ETL, EDA, data augmentation, and statistical analysis (correlation, regression).
  • Worked with Linear Regression, Decision Trees, K-Means, and Collaborative Filtering.
  • Evaluated using ROC AUC, F1-score, Precision, and Recall to optimize accuracy.
PythonEDAFeature EngineeringRecommender SystemsEvaluation

ETL Epidemiological Data Analysis

Data Engineering • Personal ProjectJul 2024 – Sep 2024

Featured

Created ETL pipelines and dashboards for epidemiological data to extract insights and visualize trends interactively.

  • Collected data using ETL pipelines and data scraping techniques.
  • Cleaned and preprocessed data to ensure accuracy and reliability.
  • Built an interactive Power BI dashboard to visualize key patterns and trends.
ETLData CleaningPower BIDashboardsTrend Analysis

Credit Card Fraud Detection

Machine Learning • Personal ProjectMar 2024 – Apr 2024

Featured

Developed and compared multiple models on an imbalanced dataset to detect fraud with strong evaluation and tuning.

  • Handled imbalanced data and conducted EDA using Python tooling.
  • Trained and tuned Logistic Regression, Random Forest, XGBoost, and Neural Networks.
  • Evaluated with Precision, Recall, F1-score, and ROC AUC.
PythonImbalanced LearningXGBoostModel TuningROC AUC

Want to see more? I can add dedicated pages for each project later, but this section is intentionally kept static and recruiter-friendly.

Skills

Tools and technologies I use to build ML systems, data pipelines, and production-ready applications.

Machine Learning & AI

Modeling, deep learning, and applied AI

10 skills
Deep LearningNeural NetworksNatural Language Processing (NLP)Large Language Models (LLMs)Model Fine-tuningFeature EngineeringData PreprocessingTime-Series AnalysisForecastingRegression / Classification

Frameworks & Libraries

Core ML + data stack

11 skills
NumPyPandasSciPyScikit-learnPyTorchTensorFlowPySpark MLFastAPIOpenCVCUDAMySQL

Data Visualization

Dashboards and storytelling

9 skills
Power BITableauMatplotlibSeabornPlotlyDashStreamlitggplot2Amazon QuickSight

Cloud & Tools

Platforms, delivery, and collaboration

8 skills
AWS (S3, EC2, Lambda, Glue)Microsoft AzureDockerCI/CD PipelinesREST APIsGit/GitHubJIRAConfluence

Analysis Methods

Statistics and experimentation

6 skills
Statistical AnalysisStatistical ModelingHypothesis TestingA/B TestingTrend AnalysisData Quality Management

Programming Languages

Primary + supporting languages

6 skills
PythonSQLR (basics)CC++Java

Utilities

Day-to-day ML workflow

7 skills
ETLEDAOptimizationPredictive ModellingJupyter NotebookVS CodeLinux / Ubuntu

Certificates

Certifications in scalable ML, Spark, analytics, and Python fundamentals.

4 total

Scalable Machine Learning with Apache Spark

Databricks

2023
Apache SparkScalable MLDatabricks

Apache Spark Programming with Databricks

Databricks

2023
Apache SparkDatabricks

Microsoft Certified: Power BI Data Analyst Associate

Udemy

2023
Power BIAnalyticsDashboards

Python Programming Bootcamp

Udemy

2021
PythonProgramming

If you want, share certificate links (Databricks/Udemy) and I’ll add a “View credential” button for each.

Languages

Languages I use for academic, professional, and everyday communication.

English

Professional proficiency

German

Basic proficiency

Currently improving

Contact

Feel free to reach out for internships, working student roles, research collaboration, or ML/AI projects.

Email Me

Get in touch

The fastest way is email. You can also connect via LinkedIn or check my work on GitHub.

Location
Germany
Email
kishansheladiya07@gmail.com
Phone
+49 176 86664054

Quick message

This form is static and opens your email client (no backend needed).