I build agentic AI systems in production.

> cat ~/.now Agentic AI systems in production

> ls ./proof AI systems in production · 40+ open-source repos

Agentic RAG
Google ADK
Vertex AI
Claude Code
Python/FastAPI
GCP

Let's talk → See work ↓

~ % ls ./metrics --prod # impact in production

−75%

processing cost

GCP data platform: faster processing and orphan-document cleanup
70 → 90%

document validation

Multi-LLM consensus (GPT + Claude + Gemini) with tuned OCR
−35%

infrastructure cost

Chat migration to agentic architecture with Google ADK + LiteLLM
3.6M+

records processed

GCP data platform (medallion) with zero data loss

~ % cat about.md

From backend to building with agents

AI Engineer. I build AI systems that actually run in production: conversational assistants, smart search over documentation, and automated document validation. I work with LLMs, Python/FastAPI and GCP, with a backend, data and operations foundation so AI doesn't stay a demo. Results this past year: document validation from 70% to 90%, ~35% lower infrastructure cost, and ~75% lower data-processing cost. I use Claude Code daily and review with multiple models before critical changes. I measure in metrics, not demos.

I also run Esem Projects , an applied-AI agency for clinics in Spain.

~ % git log --oneline work/

Cases in production

VITALY · AI Engineer ●

May 2025 – Present

Agentic AI systems in production: RAG, LLM evaluation, and a GCP data platform, with real metrics.

70→90%

validation
−75%

data cost
3.6M

records

Multi-tenant conversational assistant with an agentic architecture (orchestrator and sub-agents) on Google ADK, with multi-provider routing via LiteLLM configurable without redeploy.
Automated RAG quality evaluation subsystem (LLM-as-judge, multiple dimensions) with dataset generation at ingestion; fixed a defect that cut false negatives from 91% to nearly 0%.
Document validation pipeline via multi-LLM consensus (GPT + Claude + Gemini) with OCR: validation pass rate from 70% to 90%.
GCP data platform (BigQuery, Dataform, Dataflow; medallion architecture): 3.6M+ records processed with zero data loss, backfill 2× faster (34 → 17 min) and orphan-document cleanup; process cost reduced ~75% (from ~€1,400 to ~€300).

VITALY · Full-Stack Developer

Jun 2021 – May 2025

Java/Spring backend leading GKE migration and CI/CD.

GKE

led migration
3 meses

Dublin 2022

Strategic Middleware APIs: Designed and developed Spring-based middleware to optimize frontend/external services communication.
GKE Migration & Optimization: Led the migration to Google Kubernetes Engine, automating continuous delivery and optimizing deployments.
Post-Merger Data Integration: Actively participated in the data integration after the Preving/Cualtis merger, performing mapping and application adaptation.

VITALY · Intern Developer

Apr 2021 – Jun 2021

Received intensive training in Java Spring, Angular, Docker, and Kubernetes.
Participated in agile development teams, contributing to real-world projects and learning full software lifecycles.

~ % ls builds/