Miłosz Żeglarski
Deep Learning Software Engineer at Intel Corporation
Gdańsk, Pomeranian Voivodeship, Poland
Summary
🤩
Rockstar🎓
Top SchoolMiłosz Żeglarski is a Deep Learning Software Engineer with seven years of experience, currently building production-ready inference tooling at Intel in Gdańsk. He specializes in model serving and MLOps, contributing substantial code to OpenVINO projects—helping adapt demos to remote serving with OpenVINO Model Server and hardening server configuration and validation logic. His work spans backend engineering, model adapter design, and automation of model versioning and batching, helping bridge research models to robust deployments. Trained in computer science at Politechnika Gdańska, he combines academic grounding with hands-on open-source impact on widely used Intel model-serving infrastructure. Unusually for an engineer focused on low-latency inference, he balances deep systems-level changes with practical demo integrations that improve usability for end users.
7 years of coding experience
2 years of employment as a software developer
Magister inżynier (Mgr inż.), Computer Science, Magister inżynier (Mgr inż.), Computer Science at Politechnika Gdańska
Github Skills (14)
unit-testing10
custom-configuration10
configurations10
c-language10
inference10
deep-learning10
cprogramming-language10
yml-configuration10
system-configuration10
python10
openvino10
modello9
machine-learning8
cnn-model6
Programming languages (6)
Github contributions (5)
openvinotoolkit/model_server
Feb 2019 - Jan 2023
A scalable inference server for models optimized with OpenVINO™
Role in this project:
Back-end Developer
Back-end DeveloperContributions:1631 reviews, 267 commits, 501 PRs in 3 years 11 months
Contributions summary:Miłosz primarily focused on improving the model server's configuration parsing capabilities. They addressed issues related to required model names and paths, ensuring both are provided in single model configurations. The user's work involved changes in `config.cpp` and `ovmsconfig_test.cpp` to implement and test these validations, demonstrating a focus on improving the usability and robustness of the model server's configuration handling. The user also contributed to code related to automatic batch size enablement, and updating validation for model shapes.
pytorchscalableservingdeep-learningdag
openvinotoolkit/open_model_zoo
Nov 2021 - Jan 2022
Pre-trained Deep Learning models and demos (high quality and extremely fast)
Role in this project:MLOps Engineer
MLOps EngineerContributions:5 reviews, 17 commits, 1 PR in 2 months
Contributions summary:Miłosz's commits primarily focus on integrating and adapting various machine-learning models within the `open_model_zoo` repository, specifically to work with OpenVINO Model Server (OVMS). They introduced and modified adapters to support remote model serving, including changes to handle model versioning and input/output data transformations. Further contributions included updating several demo applications (segmentation, object detection, etc.) to utilize the OVMS adapter, enabling the use of remotely served models within these demos.
modelonnx-modelsdeep-learning-modelsmodel-zoopytorch-models
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.