Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I am an MSc graduate in Data Science from ZHAW Zurich University of Applied Sciences with practical expertise in building multilingual, LLM-powered pipelines for document understanding. I have developed agentic systems integrating technologies like GPT-4, OCR, and layout analysis to optimize workflows in retrieval-augmented generation. I am passionate about NLP applications in legal and business domains, emphasizing open-source and reproducible research. My experience spans from research internships in NLP and bioinformatics to applied machine learning projects including schema matching and clinical data analysis. I enjoy innovating with large language models and document AI to create modular, efficient solutions that handle complex multilingual data and documents.…I am an MSc graduate in Data Science from ZHAW Zurich University of Applied Sciences with practical expertise in building multilingual, LLM-powered pipelines for document understanding. I have developed agentic systems integrating technologies like GPT-4, OCR, and layout analysis to optimize workflows in retrieval-augmented generation. I am passionate about NLP applications in legal and business domains, emphasizing open-source and reproducible research. My experience spans from research internships in NLP and bioinformatics to applied machine learning projects including schema matching and clinical data analysis. I enjoy innovating with large language models and document AI to create modular, efficient solutions that handle complex multilingual data and documents.

Gaye Colakoglu





I am an MSc graduate in Data Science from ZHAW Zurich University of Applied Sciences with practical expertise in building multilingual, LLM-powered pipelines for document understanding. I have developed agentic systems integrating technologies like GPT-4, OCR, and layout analysis to optimize workflows in retrieval-augmented generation. I am passionate about NLP applications in legal and business domains, emphasizing open-source and reproducible research. My experience spans from research internships in NLP and bioinformatics to applied machine learning projects including schema matching and clinical data analysis. I enjoy innovating with large language models and document AI to create modular, efficient solutions that handle complex multilingual data and documents.…I am an MSc graduate in Data Science from ZHAW Zurich University of Applied Sciences with practical expertise in building multilingual, LLM-powered pipelines for document understanding. I have developed agentic systems integrating technologies like GPT-4, OCR, and layout analysis to optimize workflows in retrieval-augmented generation. I am passionate about NLP applications in legal and business domains, emphasizing open-source and reproducible research. My experience spans from research internships in NLP and bioinformatics to applied machine learning projects including schema matching and clinical data analysis. I enjoy innovating with large language models and document AI to create modular, efficient solutions that handle complex multilingual data and documents.

Available to hire

I am an MSc graduate in Data Science from ZHAW Zurich University of Applied Sciences with practical expertise in building multilingual, LLM-powered pipelines for document understanding. I have developed agentic systems integrating technologies like GPT-4, OCR, and layout analysis to optimize workflows in retrieval-augmented generation. I am passionate about NLP applications in legal and business domains, emphasizing open-source and reproducible research.

My experience spans from research internships in NLP and bioinformatics to applied machine learning projects including schema matching and clinical data analysis. I enjoy innovating with large language models and document AI to create modular, efficient solutions that handle complex multilingual data and documents.

Skills

Experience Level

Expert

Expert

Expert

Intermediate

Intermediate

Language

English

Advanced

German

Beginner

Work Experience

Research Intern - NLP & Document AI at NEC Laboratories Europe

July 1, 2025 - August 8, 2025

Developed an agentic system for multilingual key-value extraction and question answering on layout-rich regulatory PDFs using GPT-4o and LangGraph. Designed planner-executor-responder loops with AgentState memory and Pydantic tool schemas for modular, error-aware execution. Contributed to multilingual prompt engineering, schema-constrained validation, and ROUGE/BLEU-based evaluation for scanned (OCR) and digital PDFs.

Research Intern - Bioinformatics (Erasmus+) at Julius-Maximilians-Universität Würzburg

September 1, 2023 - August 8, 2025

Simulated nictation movement in C. elegans using behavior-tracking pipelines and analyzed large-scale phenotypic datasets. Ensured reproducibility and statistical robustness of experiments across multiple simulation runs.

ML Bootcamp Trainee at MIUUL

May 1, 2023 - August 8, 2025

Trained and evaluated classification models on real-world datasets using Scikit-learn, TensorFlow, and Keras. Improved model performance via feature engineering, hyperparameter tuning, and metric-based evaluation.

Research Intern - Bioinformatics & ML at TÜBİTAK, Würzburg, Kedi Mobile

December 31, 2022 - August 8, 2025

Performed RNA-Seq analysis using GSEA pipelines and supported mobile ML model deployment workflows. Worked across Türkiye and Germany in research settings.