LLM automation
LLM agents, prompt engineering, NLP workflows, structured outputs, and intelligent automation systems.
AI, data science and backend software engineer
I build AI-powered backend systems across machine learning, LLMs, NLP, quantum machine learning, and data science, transforming research ideas into practical engineering solutions.
Focus
My strongest work sits at the intersection of applied AI, data science, backend systems, and research-driven software.
LLM agents, prompt engineering, NLP workflows, structured outputs, and intelligent automation systems.
REST APIs, microservices, data consistency, integration flows, validation tooling, and CI/CD-ready services.
Feature extraction, model evaluation, reproducible notebooks, NLP classification, and experiment-driven development.
Healthcare AI, molecular benchmarks, peptide design, TensorFlow/PyTorch models, and domain-specific prediction systems.
Experience
A profile shaped by applied AI projects, backend service work, and research-heavy data systems.
Researching mathematical methods for aircraft wing geometry optimization and advanced aerodynamic performance.
Contributing software tools and validation components for a personalized NGS and AI-based post-transplant monitoring kit.
Firat University, 2025 - Present. Coursework in AI, NLP, and Software Architecture.
Firat University, 2021 - 2025. GPA 3.43 / 4.00, graduated with honors, top 10%.
Coursera
NVIDIA
Case Studies
These are the projects that best communicate depth: measurable outcomes, domain complexity, and production-minded implementation.
AI automation / MCP
Model Context Protocol server that turns feature descriptions and acceptance criteria into structured software artifacts.
AI product / Machine Learning
Full-stack AI product that turns natural language requirements into structured validation assets.
Healthcare AI / TEYDEB 1501
Clinical decision-support platform for non-invasive post-transplant health monitoring.
Bioinformatics / deep learning
Microplastic-binding peptide design workflow comparing multiple deep learning architectures.
Live GitHub
Cards are fetched live from GitHub, then curated so the strongest AI, data science, backend, and applied software projects appear first.
Loading live repositories from GitHub...
Stack
A focused map of the tools I use to ship AI-enabled software and validation workflows.
Python, C#, Java, SQL, Kotlin, JavaScript, Spring Boot
Machine Learning, NLP, LLMs, Quantum ML, Prompt Engineering, PyTorch, TensorFlow, Scikit-learn, LangChain, PennyLane, Qiskit
REST APIs, Microservices, API Integration, Data Validation, Postman, Apidog, Selenium, Xray, Jira
.NET, ASP.NET Core, REST APIs, Microservices, Docker, Git, Jenkins, Jupyter, CI/CD, Linux, Next.js
Writing
A Markdown-powered writing area for technical notes, project breakdowns, and implementation decisions.
Reach out for AI products, data science workflows, backend systems, applied ML projects, or research-driven software collaborations.