Batu Ozturkler
Batu Ozturkler at the Grand Canyon

Batu Ozturkler

Senior Research Scientist, Microsoft CodeAI

Hello! I am a Senior Research Scientist at Microsoft CodeAI. I am working on agentic model orchestration and routing for GitHub Copilot. My current research focuses on coordinating tool-using models, long-horizon workflows, and efficient model selection.

Previously, I worked on confidence estimation and hallucination detection in large language models, multilingual post-training for GPT-4o, and tool-using agents for Azure AI Foundry.

I received my Ph.D. in Electrical Engineering from Stanford University, where I was an NSF Graduate Research Fellow advised by John Pauly and Mert Pilanci. My doctoral work covered probabilistic reasoning with LLMs, diffusion models, robust and memory-efficient learning, and medical imaging.

Research interests: agentic AI, LLM post-training and evaluation, calibrated confidence, probabilistic reasoning, generative models, and robustness.

Outside of research, I enjoy tennis, soccer, hiking, and an overly competitive game of pool.

Email Google Scholar GitHub X LinkedIn Résumé

Experience

Microsoft / CodeAI

Senior Research Scientist

Aug 2026 – Present

Research Scientist II

Feb 2026 – Aug 2026

  • Train coordinator LLMs to compose tool-using workflows and route each step to an appropriate model.
  • Developed prompt-cache-preserving routing for long-horizon conversations; matched an always-strong baseline within 0.3 percentage points on SWE-bench Verified while reducing model cost by 54%.
  • Led development of a fine-tuned ModernBERT credential scanner deployed across GitHub products at the scale of all GitHub push traffic, reducing inference cost by over 98% and latency by over 90%.

Applied Scientist II

May 2024 – Feb 2026

  • Developed post-training methods for calibrated confidence estimation and hallucination detection in production language and vision-language systems.
  • Co-developed multilingual post-training for GPT-4o across mid-training, SFT, DPO, and RLHF; built evaluation and synthetic-data pipelines.
  • Designed tool-calling, retrieval, and search workflows for Azure AI Foundry Agents and improved response latency by 30% without reducing quality.

Stanford University

Postdoctoral Scholar

Mar 2024 – May 2024

Research Assistant

Sep 2019 – Jan 2024

  • Developed memory-efficient training methods and self-supervised augmentation for robust MRI reconstruction.
  • Developed equivalent convex formulations of non-convex neural networks with robustness, interpretability, and convergence guarantees.

Research internships

NVIDIA · Research Intern

Sep 2022 – Apr 2023

Worked on robust diffusion models under distribution shifts for MRI reconstruction with Chao Liu and Jan Kautz.

Microsoft Research · Research Intern

Jun 2022 – Aug 2022

Worked on probabilistic inference for in-context learning with large language models under the supervision of Nebojsa Jojic.

ETH Zürich · Research Intern

Jun 2018 – Aug 2018

Worked on ultrasound imaging in the Computer Vision Lab with Orcun Goksel.

Selected publications

Google Scholar

  1. ThinkSum: Probabilistic Reasoning over Sets Using Large Language Models.
    B. Ozturkler, N. Malkin, Z. Wang, N. Jojic. ACL 2023.

    Paper

  2. SMRD: SURE-based Robust MRI Reconstruction with Diffusion Models.
    B. Ozturkler, C. Liu, B. Eckart, M. Mardani, J. Song, J. Kautz. MICCAI 2023, early accept (top 15%).

    Paper

  3. RED-diff: Regularization by Denoising Diffusion Process for MRI Reconstruction.
    B. Ozturkler, M. Mardani, A. Vahdat, J. Kautz, J. Pauly. NeurIPS 2023 Workshop on Deep Learning and Inverse Problems.

    Paper

  4. Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers.
    A. Sahiner, T. Ergen, B. Ozturkler, J. Pauly, M. Mardani, M. Pilanci. ICML 2022.

    Paper

  5. VORTEX: Physics-Driven Data Augmentations for Consistency Training for Robust Accelerated MRI Reconstruction.
    A. D. Desai, B. Gunel, B. M. Ozturkler, H. Beg, S. Vasanawala, B. A. Hargreaves, C. Ré, J. M. Pauly, A. S. Chaudhari. MIDL 2022, Best Paper Award.

    Paper

  6. Demystifying Batch Normalization in ReLU Networks: Equivalent Convex Optimization Models and Implicit Regularization.
    T. Ergen, A. Sahiner, B. Ozturkler, J. M. Pauly, M. Mardani, M. Pilanci. ICLR 2022.

    Paper

Education

Stanford University

Ph.D. in Electrical Engineering · GPA 3.99/4.00

2019 – 2024

Advisors: John Pauly and Mert Pilanci. Thesis: Efficient and robust deep learning for medical imaging and natural language processing.

Stanford University

M.S. in Electrical Engineering · GPA 3.99/4.00

2019 – 2021

Middle East Technical University

B.S. in Electrical Engineering · GPA 3.96/4.00 · Rank 3/413

2015 – 2019

Honors

  • NSF Graduate Research Fellowship
  • Stanford EE Departmental Fellowship

Service

Reviewer for ACL, NeurIPS, ICML, ICLR, MICCAI, and IEEE Transactions on Medical Imaging.

Program Committee, ICML Workshop on Knowledge and Logical Reasoning.