Dan Blanaru
AI DevTech Enginner at NVIDIA
Munich, Bavaria, Germany
Summary
🤩
Rockstar🎓
Top SchoolDan Blanaru is an AI DevTech engineer based in Munich with seven years of experience optimizing ML models for edge and accelerated inference, currently focusing on LLM inference performance at NVIDIA. He brings deep C++ performance engineering skills informed by hands-on work in LLM quantization for custom AI accelerators and prior research on pruning, quantization-aware training, and deployment of CNNs on edge devices. His background spans data science and regulated medical analytics to large-scale fraud detection, demonstrating an ability to translate research into production systems that reduced costs and resource usage. Notably, he has improved training throughput by 30% and slashed RAM requirements by ~80% in past projects, showing a pragmatic focus on latency-accuracy and resource trade-offs. Educated at TUM with a computer science bachelor's from Iași, he combines rigorous academic training with practical accelerator-aware model optimization.
7 years of coding experience
1 year of employment as a software developer
Bachelor's degree, Computer Science, Bachelor's degree, Computer Science at Universitatea „Alexandru Ioan Cuza” din IașiMaster's degree, Data Engineering and Analytics, Master's degree, Data Engineering and Analytics at Technical University of Munich
English, Romanian
Github Skills (13)
nvidia9
tensorrt8
sdk7
throughput7
latency7
optimizer7
deep-learning6
inference6
low-latency5
high-performance5
machine-learning5
tensorflow4
gpu-acceleration3
Programming languages (2)
Github contributions (5)
DanBlanaru/rl-ticket
May 2020 - Jun 2020
Contributions:9 pushes, 1 branch in 26 days
DanBlanaru/MiniNN
Jan 2020 - Jan 2020
Contributions:16 pushes, 1 branch in 8 days
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.