Sinem Demirci

Istanbul, Turkey ·+90(542)6011282 · sinemciftcidemirci@gmail.com

AI Engineer with a Master's in Computer Engineering (AI focus), skilled in deploying ML pipelines, optimizing models, and integrating generative AI for real-world impact. Experienced in NLP, model evaluation, and visual generation workflows. Currently building FersmithAI, a SaaS platform for personalized AI/ML learning, as a solo founder.


Experience

AI/ML Engineer

Freelance

Fine-tuned and evaluated 15+ transformer models on Turkish children’s literature. Built and deployed NLP tools via Flask and Streamlit with visual generation using Stable Diffusion.

October 2024 - Present

Data Analyst Intern

Uptrail

Completed a remote data analyst internship, gaining hands-on experience in data analysis workflows and reporting.

July 2025 - August 2025

Cabin Attendant

Turkish Airlines

Delivered consistent performance in high-stakes international operations requiring crisis management and multilingual communication. Strengthened soft skills transferable to cross-functional AI teams.

January 2020 - Present

Translator

Freelance

Translated academic and creative texts (EN<->TR) with precision and deadline discipline. Built a strong foundation in text quality, structure, and linguistic nuance — essential in NLP.

September 2014 - December 2019

Education

Yildiz Technical University

Master's of Science
Computer Engineering - Information Technologies

GPA: 3.14/4.00

October 2023 - February 2025

Istanbul University

Bachelor's of Science
Faculty of Engineering - Chemical Engineering
September 2011 - July 2019

Anadolu University

Bachelor's of Arts
Open Education Faculty - Business Administration
September 2013 - January 2021

Skills

Programming Languages & Tools
Libraries, Tools & Platforms
  • Hugging Face Transformers & Datasets
  • PyTorch, TensorFlow, Scikit-learn, Keras
  • Pandas, NumPy, Matplotlib, Streamlit
  • Flask API Deployment
  • Stable Diffusion, OpenCV
  • LangChain, RAG, Vector Databases (FAISS, Chroma)
  • Claude API, OpenAI API
  • SQL, Jupyter Notebook
  • Git & GitHub, Google Colab, VS Code, PyCharm
Workflow
  • Model Evaluation (ROUGE, BERTScore, Accuracy)
  • Agile & Rapid Prototyping
  • Documentation & Public Repos
  • Experiment Tracking & Dashboarding
  • Cross-functional Communication
  • Multilingual NLP (TR/EN)

Projects

FersmithAI: Personalized AI/ML Learning Platform In Progress
A full-stack SaaS platform delivering personalized AI/ML learning roadmaps for technical professionals. Built solo with Next.js 14, Supabase (PostgreSQL + Auth), and Tailwind CSS. Features a 140-question adaptive assessment engine, dynamic skill graph with real-time progress tracking, and Google OAuth. Currently live as a waitlist — subscription model coming soon.

FersmithAI Waitlist FersmithAI Onboarding

Visit fersmith.ai

SkyAnalyst-AI: Cabin Operations Intelligence Framework
A modular NLP framework that transforms unstructured flight cabin reports into structured operational insights using RAG and abstractive summarization. Built on ChromaDB vector storage and all-MiniLM-L6-v2 embeddings for semantic retrieval across 2,500+ synthetic incident reports — enabling meaning-based search that goes beyond keyword matching. Summarization is powered by DistilBART-CNN, delivering 4x faster inference than standard BART with negligible quality loss. Includes an exploratory analytics dashboard with sentiment intensity scoring and statistical visualizations across 5 incident categories and 22 flight routes.

SkyAnalyst Homepage SkyAnalyst Tab 2 SkyAnalyst Kitchen Malfunction

View on GitHub

Transformer-Based Summarization & Evaluation
Fine-tuned and evaluated multiple transformer models (BERT, T5, mT5) for Turkish children’s literature. Integrated Flask API, and Stable Diffusion to generate visual illustrations. 90% of users found the visuals well-aligned with the story content.

Summarization Output

View on GitHub

Meat Quality Detection
Developed a TensorFlow-based image classification system to detect spoiled meat. Applied data augmentation and evaluated model performance with accuracy and loss metrics.

Meat Detection Output

View on GitHub


Certificates

  • Data Analyst Internship – Uptrail
  • Deep Learning A-Z: Neural Networks, AI – Udemy
  • Machine Learning A-Z™: AI, Python & Data Science – Udemy
  • 100 Days of Code: Python Pro Bootcamp – Udemy
  • SQL for Data Analysis – Udemy
  • NLP for Text Summarization – Udemy