prof_pic.jpg

Doğaç Eldenk

Evanston, IL
[email protected]

I am currently a Master’s student at Northwestern University, studying Computer Science. I worked at Carbon Health as a Software Engineer for over 4 years. I’m doing research with Prof. Stephen Xia in the Intelligent and Mobile Embedded Computing (IMEC) Lab in the areas of distributed AI/ML systems and efficient architectures.

I am looking for research engineer roles & internships on the following,

  • Distributed AI/ML algorithm design and optimization
  • Novel AI/ML architecture design and implementation
  • Edge AI/ML model design and deployment
  • AI/ML tooling and infrastructure development
  • Supervised fine-tuning and reinforcement learning for LLM alignment
  • Interactive AI agents and multi-agent systems

I occasionally write blog posts about topics that I find interesting, mostly related to software.

latest posts

publications

  1. microservice.png
    Incidents During Microservice Decomposition: A Case Study
    Doğaç Eldenk and H. Alperen Çetin
    In 29th International Conference on Evaluation and Assessment in Software Engineering (EASE), 2025
  2. unsup.png
    Learning portrait drawing with unsupervised parts
    Burak Tasdemir, Mustafa Goktan Gudukbay, Dogac Eldenk, and 2 more authors
    International Journal of Computer Vision, 2024

selected projects

  1. DeepSeek OCR – Apple Metal (MPS) & CPU support
    Updated version of DeepSeek-OCR model to support non-CUDA backends, MPS and CPU. 200+ Downloads on Hugging Face.
  2. Uniference – Discrete Event Simulation
    (Paper on-submission) A discrete event simulator for running, developing and evaluating distributed inference algorithms.
  3. Defenchess – AI Chess Engine
    A high-performance C++ engine for advanced chess analysis and play. Previously ranked in the top-10 worldwide with a 3400+ ELO performance.
  4. kotlinx-protobuf-gen
    Generate kotlin data classes from protobuf files that supports Kotlin Native that can be serialized and deserialized to protobuf using `kotlinx.serialization`.