Hi there! I’m Ruslan Magana Vsevolodovna
Senior AI Engineer — building governed, production-grade agentic AI.
I design and ship multi-agent AI platforms that actually hold up in enterprise environments — combining reasoning, execution, safety, and cost-awareness into systems that are reliable, not just demos. My work spans LLM applications, national-scale data platforms, and cloud-native MLOps.
Before AI engineering, I trained as a physicist (PhD) — and the same research-driven mindset I used to study the universe now goes into building scalable, secure AI infrastructure.
Quick facts: PhD in Physics · AI, cloud, and MLOps experience · open-source AI tools and tutorials · fluent in four languages.
What I work on
- Agentic & multi-agent systems — orchestration, reasoning, tool use, and safety enforcement with MCP, LangGraph, CrewAI, and BeeAI.
- Generative AI & LLMs — RAG, fine-tuning (PEFT/LoRA), and prompt engineering with Hugging Face and PyTorch.
- Cloud-native MLOps — Kubernetes/OpenShift, Docker/Podman, Terraform, and CI/CD across AWS, Azure, Google Cloud, and IBM Cloud.
My journey
I work as a Senior AI Engineer building enterprise multi-agent AI platforms in production. Earlier, I held data science and data engineering roles across tech and consulting, and I began my career as a postdoctoral researcher in nuclear physics at INFN (Genoa) — analyzing NUMEN-project data and publishing peer-reviewed work on nuclear structure and neutrinoless double-beta decay.
→ Publications · Projects
Beyond work
When I’m not building AI systems, I’m usually with my family — traveling, and learning the culture and languages of each new place. I also enjoy writing about Agentic AI, Data Science, and Cloud Engineering on my blog, and sharing talks on YouTube. You’ll find my open-source work on GitHub.
