> Markdown version of [/@dmitry-mironov](https://www.wearedevelopers.com/@dmitry-mironov). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Dmitry Mironov
NVIDIA architect building systems for large-scale, low-latency LLM inference.

## About

Dmitry Mironov builds machine learning infrastructure as a Senior Deep Learning Solutions Architect at NVIDIA. He focuses on the efficient, large-scale deployment of large language models and optimizing their inference.

Before joining NVIDIA, he was the co-founder and CTO of a startup where he integrated computer vision systems into the gold mining, transportation, and energy sectors. Today, he teaches developers how to optimize model serving, co-authoring NVIDIA workshops on sizing inference systems and deploying speculative decoding techniques for low-latency compute.



## Past Sessions

### World Congress 2026 Europe · July 8, 2026
Berlin, Germany
- [Faster Together: Train and Deploy a Speculative Decoding Model for Low-Latency LLM Inference](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/1142-faster-together) · 120 min




## Links

- [LinkedIn](https://www.linkedin.com/in/dmitry-mironov/)