I turn noise into signal and signal into systems
6+ years at Elmec Informatica, from Service Desk to the AI team.
Work
LLM Gateway
OpenAI-compatible LLM gateway in Go: one API in front of OpenAI, Anthropic, and on-prem models (vLLM, Ollama), with token-level access control, RBAC, budgets, rate limiting, and OpenTelemetry observability, plus a 40-tool MCP admin server. In production at Elmec.
Phishing Email Triage
FastAPI service that parses incoming emails and scores phishing risk with an LLM, wired into the cybersecurity team’s ticketing flow. Langfuse-managed prompts, deployed on Kubernetes, and the basis for my public AI & Security talks.
AI Documentation Assistant
LLM workflows for technical authors: validates draft sections against guidelines and offers suggest / rework / extract actions, streamed token-by-token. Structured output via Instructor, prompts in Langfuse, deployed on Kubernetes.
Generative UI Dashboard
Upload a CSV / Excel / JSON file and get an interactive dashboard: one LLM call maps columns to chart specs, then everything renders deterministically through ECharts templates, with no generated code. Drag-and-drop layout, SSE streaming. Earlier iterations explored agentic generation.
The path
- 04/2024 – Present · Brunello (VA)
AI Engineer & Data Scientist
Elmec Informatica S.p.A.Technical reference for the AI team on LLM, RAG and MLOps; owns the hybrid deployment strategy and observability standard.
50% Doc creation time saved35–40% Classification savings1,900+ Monthly interactions~79 Hours saved / month - 04/2021 – 04/2024 · Brunello (VA)
System Engineer & Business Data Analyst
Elmec Informatica S.p.A.Stabilized Windows / Linux, cloud and virtualization; automated ops with Python / PowerShell and pioneered the first ML on ticketing.
- 01/2020 – 04/2021 · Brunello (VA)
Service Desk Specialist
Elmec Informatica S.p.A.L1/L2 incident and escalation management with ITSM: the foundation of technical analysis and communication.
Capabilities
I don’t just use the stack — I set the standards the team builds on.
Generative AI & LLM
LLMs · Generative AI · RAG · Agentic AI · Agent Orchestration · Prompt Engineering · LLM-as-a-Judge · Responsible AI · Conversational AI · Intent Detection
LLM Providers & Deployment
OpenAI · Azure OpenAI · Anthropic · vLLM (focus) · LocalAI · LM Studio · Ollama
MLOps & Observability
Langfuse · MLOps pipelines · Experiment Tracking · CI/CD for ML · Model Monitoring
Vector Databases & Search
Qdrant (cert) · ChromaDB · LanceDB · OpenSearch · Hybrid Search · Re-ranking
Frameworks & Programming
Python · LangChain · LlamaIndex · HuggingFace · Transformers · FastAPI · Flask · Gradio · Pydantic AI · Agno · React · SQL · PowerShell · Bash
Data Science & Visualization
NLP · Predictive Modeling · Classification · Automated EDA · ECharts · Plotly · Qlik Sense · Matplotlib · Seaborn
Cloud, DevOps & Infrastructure
AWS · Azure · Docker · Kubernetes · Git · VMware · Hyper-V · Linux · Windows Server
Recognition & Credentials
Talks — 7 (1 external)
Certifications
Education
Let’s connect
Let’s turn your noise into signal.
Open to conversations about production AI, LLMs, and MLOps. Reach me on LinkedIn.
LinkedIn