AI & ML Engineer · NLP Researcher
Building production-grade multimodal AI systems, autonomous agents, and NLP pipelines.
Independent research on tokenization, word representations, and retrieval
for low-resource and agglutinative languages.
Morpheus: A Morphology-Aware Neural Tokenizer and Word Embedder for Turkish arXiv preprint, 2026 — sole author
A lossless, morphology-aware neural tokenizer and word embedder for Turkish. A differentiable Poisson–binomial soft segmentation produces exact, surface-preserving morpheme splits (decode(encode(w)) = w), while the same forward pass yields structured word embeddings. Achieves the lowest BPC among reversible tokenizers and roughly 2× the morphological alignment of BPE, WordPiece and Unigram, and leads BERTurk and BGE-M3 on lexical retrieval.
Maximizing RAG Efficiency: A Comparative Analysis of RAG Methods Natural Language Processing, Cambridge University Press (SCI Q1), 2025
A grid-search study of 23,625 configurations across vector stores, embedding models and LLMs on cross-domain data, quantifying the trade-offs between retrieval quality, similarity-based ranking, token usage, runtime and hardware utilization. Contextual compression filters substantially reduce token consumption and hardware load, at a similarity cost that is often acceptable depending on the RAG method and use case.
Ongoing work lives under lonewolf-rd. Released models and demos are on lonewolflab.
| Project | Description |
|---|---|
| TurkishMorpheus | Lossless, morphology-aware neural tokenizer and word embedder for Turkish |
| Project | Tech Stack |
|---|---|
| RAG Optimization |    |
| Multi-Modal RAG |  |
| TalkYou |     |
| LLMRoboFund |  |
| Project | Tech Stack |
|---|---|
| Olivetti Face Recognition |  |
| MobileNetV1 — Julia |    |
| EfficientNetV2 Transfer Learning |  |
| Food Vision | |
| Fashion MNIST | |
| Financial Sentiment Classifier | |
| Project | Tech Stack |
|---|---|
| Electricity Price Forecasting |  |
| Bitcoin Price Forecasting |   |
| Bike Sharing Demand |    |
| Bank Deposit Prediction | |
| Credit Score Prediction | |
| Econ Dashboard | |
Open to research collaboration on tokenization, representation learning and retrieval for morphologically rich languages — tolgasa2@gmail.com