Work Experience

Research roles across an academic lab and industry, from open-source Turkish models to on-device and domain-specialized systems.

Research experience

Oct 2025 - Present

Baykar Technology

LLM & VLM Researcher

Domain-specialized vision-language and language models for onboard and on-device deployment; agentic tool calling; evaluation of Turkish LLMs.

Integrated a domain-adapted VLM directly onto UAV's, enabling decision-making at the edge.
Shipped an on-device mobile LLM agent with tool calling company-wide, helping task management and internal workflows.
Architected a fully autonomous LLM news agency, automating the process from source collection and evaluation to scheduled publishing.
Conducted LLM/VLM training at scale, including large-scale dataset generation and preprocessing.
Conducted research and development on domain-specialized language models for aviation applications.
Developed agentic AI systems and AI-driven features to enhance applications across several team projects.
Contributed to a comprehensive evaluation framework for Turkish LLMs.

Methods & toolsms-swiftverlPEFTvLLMONNXEdge AILangChainLangGraph

Jul 2024 - Present

YTU COSMOS AI Research Lab

NLP Research Fellow

Open-source Turkish language, vision-language and embedding models; efficient inference; large-scale data curation; distributed training on HPC clusters.

Developed state-of-the-art open-source Turkish LLMs, VLMs and embedding models.
Curated and published large-scale open-source textual and multimodal datasets with multi-million examples.
Created ChainFlow, a novel flow matching speculative decoding method surpassing Eagle3 and DFlash in vLLM backend.
Research grants from the Barcelona Supercomputing Center (BSC), Türkiye's HPC Center and national funding.
Ran several distributed multi-node training, deployment and evaluation on Slurm-managed HPC clusters.

OutputsModernBERT-TR ChainFlow

Methods & toolsSlurmDeepSpeedPyTorchTransformersDistributed multi-node trainingSpeculative decodingFlow matching

Jun 2025 - Aug 2025

Baykar Technology

Research Intern (NLP)

Domain adaptation and language acquisition in LLMs; advanced RAG.

Researched domain adaptation and language acquisition in LLMs.
Researched and evaluated advanced RAG variants (e.g. Self-RAG, Adaptive-RAG, RAPTOR and others) and built institutional RAG systems for internal AI-assisted workflows.

Engineering experience

Aug 2025 - Oct 2025

ASELSAN

Software Engineering Intern

Flight-simulation components and networking modules for defense applications.

Developed a flight simulation with TCP/UDP communication protocols and integrated it into existing ASELSAN software, enabling the simulation to run across the world.
Built data-communication simulations used by several teams, speeding up the tuning and debugging of communication protocol development.

Methods & toolsCC++TCP/UDP