Tuna Kömürcü

CV

The same content as the PDF résumé, laid out to actually read on screen.

Download PDF

Education

TOBB University of Economics and Technology, Ankara

2021 – 2026

B.S. in Artificial Intelligence Engineering — focus on machine learning, deep learning, NLP, and software architecture.

Graduation project — an 8-module, human-in-the-loop multi-agent LLM system automating antitrust legal investigation workflows, built with a 4-person team. See ACLISS on Key Projects.

Experience

AI Engineering Intern / Developer — Mikrogrup

May 2026 – Aug 2026

  • Developed MomTest AI end-to-end, automating structured customer-discovery workflows for business validation.
  • Designed an agent loop using function calling and structured outputs, with strict guardrails against leading-question bias.
  • Deployed and operated the production environment on AWS (EC2, S3, IAM, CloudWatch) and built unit/integration test suites.
  • Owned model training and fine-tuning for a CAPTCHA OCR model, raising recognition accuracy from 41% to 93%.

AI Engineering Intern / Developer — Başarı Mobile

Sep 2025 – Jan 2026

  • Designed and built a database-agnostic Text2SQL agent end-to-end, from architecture through prompt engineering.
  • Built a hybrid retrieval (dense + BM25) architecture with Qdrant (HNSW) for dynamic schema retrieval and selection.
  • Reached ~95% accuracy on simple queries and ~85% on medium-complexity queries.
  • Load-tested with Locust and monitored latency (p50/p95/p99) via Prometheus & Grafana.

AI Engineering Intern — Havelsan Technology Radar

Sep 2024 – Jan 2025

  • Designed and trained an edge-attentive residual CNN from scratch to denoise raw radar imagery.
  • Implemented hybrid activation and loss functions to preserve high-frequency structural detail.
  • Applied ensemble learning across multiple architectures and managed the end-to-end training pipeline.

Skills

Programming Languages

PythonJavaSQL

Machine Learning & Deep Learning

PyTorchTensorFlowscikit-learnFine-tuning / Transfer LearningLoRA / PEFTComputer VisionONNX

NLP, LLMs & Vector Search

RAGLangChainLangGraphPrompt EngineeringFunction Calling / Structured OutputGuardrails & LLM EvaluationMulti-Agent SystemsModel Quantization (GGUF, llama.cpp)Vector Databases (Qdrant, FAISS, Chroma)Hybrid Retrieval (Dense + BM25)

Data Analysis & Engineering

NumPyPandasPostgreSQLEDAFeature EngineeringJupyter

MLOps, Cloud & Deployment

AWS (EC2, S3, IAM, CloudWatch, Secrets Manager)DockerNginxCI/CDFastAPIVercelPrometheus & Grafana

Projects

Full write-ups — problem, architecture diagrams, technical decisions, and results — live on Key Projects rather than repeated here.

View Key Projects →