PMO & Project Controller — governo le commesse, automatizzo le operationsPMO & Project Controller — governing engagements, automating operations
Delivery e governance PMO enterprise per CNH Industrial,Porini,Digital Thinks — un portafoglio di commesse IT in parallelo, un team di 7 PM in matrice, €1,8M+ di spesa in meno in 12 mesi. Da marzo 2025 progetto, costruisco e opero 10+ sistemi AI end-to-end, in produzione 24/7.Enterprise PMO delivery and governance for CNH Industrial,Porini,Digital Thinks — a portfolio of concurrent IT engagements, a 7-PM team in a matrix, €1.8M+ less spend in 12 months. Since March 2025 I design, build and operate 10+ end-to-end AI systems, in 24/7 production.
corsi erogati al mese, da 15courses delivered a month, up from 15
7
PM coordinati in matricePMs coordinated (matrix)
€1.8M+
risparmi in 12 mesisavings in 12 months
10+
sistemi in produzione 24/7systems in 24/7 production
~8h→~2h
reporting settimanale del team PMOweekly reporting of the PMO team
01// Il profilo// The profile
Il ponteThe bridge
Due competenze che raramente convivono nella stessa persona.Two skill sets that rarely live in the same person.
Governance enterpriseEnterprise governance
PMO multi-cliente: portafoglio di commesse IT in parallelo, forecast di ricavi e confronto mensile con il consuntivoMulti-client PMO: portfolio of concurrent IT engagements, revenue forecasting and monthly comparison against actuals
Licenze multi-milione: €1,8M+ di spesa in meno in 12 mesi su CNH IndustrialMulti-million licensing: €1.8M+ less spend in 12 months at CNH Industrial
Governance applicata all'AI: registro di claim verificati anti-allucinazione, quality gate umano, purge documentato dei contenuti fabbricatiGovernance applied to AI: anti-hallucination registry of verified claims, human quality gates, documented purge of fabricated content
FinOps applicato: cost tracking multi-provider cloud, budget cap per servizio, placement dei workload guidato dai costiApplied FinOps: multi-provider cloud cost tracking, per-service budget caps, cost-driven workload placement
10+ sistemi progettati e gestiti in esercizio continuo10+ systems designed and run in continuous production
LLM orchestration, RAG, data pipeline, observability — sistemi veri in produzioneLLM orchestration, RAG, data pipelines, observability — real systems in production
Effort di sviluppo stimati e contestati con cognizione di causaDev effort estimated and challenged with first-hand knowledge
Consulente PMO e automazionePMO & Automation Consultant— IndipendenteIndependent
Mar 2025 – oggipresent
Torino · Scelta strategica: colmare il gap tra governance e delivery tecnica.Turin · Strategic choice: closing the gap between governance and technical delivery.
Progettato e messo in produzione un portfolio di 10+ sistemi AI/automation end-to-end su un backbone architetturale condiviso, gestendo in autonomia l'intero ciclo: discovery, architettura, sviluppo, deploy, observability ed evoluzione.Designed and shipped a portfolio of 10+ end-to-end AI/automation systems on a shared architectural backbone, owning the full lifecycle solo: discovery, architecture, development, deployment, observability, evolution.
Gestita infrastruttura self-hosted in produzione 24/7: 25+ container Docker, VPN mesh, monitoring centralizzato, backup automatizzati — stessi pattern enterprise (alta disponibilità, telemetria, security by design), a scala personale/small-team.Operated self-hosted 24/7 production infrastructure: 25+ Docker containers, VPN mesh, centralized monitoring, automated backups — the same enterprise patterns (HA, telemetry, security by design), at personal/small-team scale.
Un engagement commerciale consegnato a un cliente esterno (startup torinese): piattaforma di lead generation B2B con CRM, scoring e go-to-market.One commercial engagement delivered to an external client (Turin startup): B2B lead-generation platform with CRM, scoring and go-to-market.
Comprensione diretta di come l'AI trasforma l'SDLC e la stima degli effort — uso quotidiano di coding agent (Claude Code, Cursor, Antigravity), prompt engineering, pattern di orchestrazione.First-hand understanding of how AI reshapes the SDLC and effort estimation — daily use of coding agents (Claude Code, Cursor, Antigravity), prompt engineering, orchestration patterns.
PMO & Project Controller — DGS S.p.A.
Lug 2021 – Mar 2025Jul 2021 – Mar 2025
Italia (ibrido) · Delivery e governance per un cliente automotive e due società del gruppo DGS.Italy (hybrid) · Delivery and governance for an automotive client and two DGS group companies.
Digital Thinks— Project Manager· Ott 2024 – Mar 2025Oct 2024 – Mar 2025
Ridisegno della pipeline di erogazione (commesse, fatturazione, contrattualistica) e gestione del SAL settimanale (stato avanzamento lavori) sulle commesse formative.Redesigned the delivery pipeline (engagements, billing, contracts) and ran the weekly work-progress review (SAL) across training engagements.
Throughput formativo più che triplicato (da ~15 a 50+ corsi/mese), con dashboard Power BI real-time sui KPI critici e coordinamento di 5 fornitori tecnici.Training throughput more than tripled (from ~15 to 50+ courses/month), with real-time Power BI dashboards on critical KPIs and coordination of 5 technical vendors.
Porini— PMO· Lug 2022 – Ott 2024Jul 2022 – Oct 2024
PMO end-to-end su un portafoglio multi-cliente di commesse IT in parallelo, inclusi progetti di migrazione cloud (Azure, AWS): forecast di ricavi e confronto mensile con il consuntivo.Ran end-to-end PMO across a multi-client portfolio of concurrent IT engagements, including cloud migration projects (Azure, AWS): revenue forecasting and monthly comparison against actuals.
Coordinato in matrice un team di 7 Project Manager (assignment, prioritizzazione, quality gate, escalation — senza riporto gerarchico).Coordinated a 7-Project-Manager team in a matrix (assignments, prioritization, quality gates, escalation — no line management).
Governance automatizzata (Jira custom + Power BI live + template Confluence): reporting da ~8 a ~2 ore a settimana.Automated governance (custom Jira + live Power BI + Confluence templates): reporting from ~8 to ~2 hours a week.
Con il team, ridotta la spesa licenze software del reparto con analisi dell'utilizzo reale, licenze condivise su server remoto e negoziazione coi vendor: oltre €1,8M in 12 mesi su €5,2M/anno, circa un terzo.With the team, cut the department's software license spend via real-usage analysis, shared licenses on a remote server and vendor negotiation: over €1.8M in 12 months on €5.2M/year, about a third.
Gestione dell'infrastruttura server virtualizzata (ambienti R&D, telemetria macchinari) e del lifecycle/obsolescenze del parco workstation e server.Managed the virtualized server infrastructure (R&D environments, machinery telemetry) and the lifecycle/obsolescence of the workstation and server estate.
Change management e adoption tool su team Italia–USA–India. Supportato l'avvio dei poli di Racine (USA) e New Delhi (India) con rollout di tool e licenze.Change management and tool adoption across Italy–USA–India teams. Supported the launch of the Racine (USA) and New Delhi (India) hubs with tool and license rollout.
Consulente finanziarioFinancial Advisor— ING Italia
Apr 2019 – Giu 2021Apr 2019 – Jun 2021
Gestione portafoglio clienti, analisi profili di rischio e pianificazione patrimoniale in contesto regolamentato.Client portfolio management, risk-profile analysis and wealth planning in a regulated context.
03// Sistemi in produzione// Production systems
Sistemi in produzioneProduction systems
Il differenziatore: sistemi reali, costruiti e operati in prima persona, con metriche verificabili sul codice.The differentiator: real systems, built and operated first-hand, with metrics verifiable on the code.
Produzione 24/7 su infrastruttura self-hosted (mini-server x86 + nodo ARM64 di riserva), scala personale/small-team. Codice privato — architettura, demo e walkthrough su richiesta.24/7 production on self-hosted infrastructure (x86 mini-server + ARM64 standby node), personal/small-team scale. Private code — architecture, demos and walkthroughs on request.
in produzione dal 2025 · oggi v2in production since 2025 · now v2~/systems/ai-gateway
v1, costruita da zero (2025–26): gateway self-hosted compatibile OpenAI con routing adattivo su più fornitori, rate limiting, failover automatico e osservabilità. v2, in produzione oggi (181 deployment di modelli su 9 provider): quando il problema vero si è spostato dal routing intelligente all'aggregazione e rotazione di quote multi-provider, ho ritirato la v1 e ricostruito su un motore open-source maturo — failover, policy di quota e di costo (budget cap per provider) e hardening restano progettati e operati da me.v1, built from scratch (2025–26): self-hosted OpenAI-compatible gateway with adaptive routing across multiple providers, rate limiting, automatic failover and observability. v2, in production today (181 model deployments across 9 providers): once the real problem shifted from intelligent routing to aggregating and rotating multi-provider quotas, I retired v1 and rebuilt on a mature open-source engine — failover, quota and cost policy (per-provider budget caps) and hardening remain designed and operated by me.
9
providerproviders
181
model deploymentmodel deployments
x86 + ARM
self-hosted
decisioni & tradeoffdecisions & tradeoffs
Thompson sampling al posto di una classifica statica dei provider: i free-tier degradano in modo imprevedibile — la qualità reale va appresa in continuo (explore/exploit), non scritta a mano.Thompson sampling instead of a static provider ranking: free tiers degrade unpredictably — real quality has to be learned continuously (explore/exploit), not hand-ranked.
Rate limiting GCRA invece di finestre fisse: flusso levigato, niente raffiche al reset della finestra.GCRA rate limiting instead of fixed windows: smooth flow, no thundering herd at window reset.
Il costo vero del build non è scriverlo, è mantenerlo: la v1 valeva quel costo finché il routing era il differenziatore. Quando ha smesso di esserlo, il costo è rimasto e il valore no — da lì la v2.The real cost of building isn't writing the code, it's maintaining it: v1 was worth that cost while routing was the differentiator. When it stopped being one, the cost stayed and the value didn't — hence v2.
Personal AI Knowledge SystemPersonal AI Knowledge System
R&D
"Secondo cervello": knowledge graph temporale + retrieval ibrido a 3 lane (denso + BM25 + graph walk, fusione RRF) con variante HippoRAG-2 su Personalized PageRank. Agente proattivo con confidence-routing e critic anti-contraddizione."Second brain": temporal knowledge graph + 3-lane hybrid retrieval (dense + BM25 + graph walk, RRF fusion) with a HippoRAG-2 variant on Personalized PageRank. Proactive agent with confidence-routing and an anti-contradiction critic.
decisioni & tradeoffdecisions & tradeoffs
Fusione RRF invece di un reranker addestrato: niente training data, comportamento spiegabile, ogni lane degrada in isolamento.RRF fusion instead of a trained reranker: no training data needed, explainable behavior, each lane degrades in isolation.
L'eval A/B ha smontato il mio stesso numero: recall@10 0,55 era un artefatto di un corpus con ~45% di duplicati (corretto: 0,85). Prima l'igiene dei dati, poi le feature.The A/B eval broke my own number: recall@10 of 0.55 was an artifact of a corpus with ~45% duplicates (corrected: 0.85). Data hygiene first, features second.
Critic anti-contraddizione + confidence-routing: sotto soglia il sistema tace — meglio nessuna risposta che una allucinata.Anti-contradiction critic + confidence routing: below threshold the system stays silent — no answer beats a hallucinated one.
5 output channel5 output channelsRAG · KG
Lead-Gen B2B per startupB2B Lead-Gen for a startup
Piattaforma full-stack di finanza personale: 9 engine analitici schedulati (forecast, anomaly, Monte Carlo sulla probabilità di rovina), 4 feature LLM con degradazione controllata (chat text-to-SQL sandboxed), security rewrite documentata (WebAuthn, CSRF, CSP).Full-stack personal-finance platform: 9 scheduled analytics engines (forecast, anomaly, Monte Carlo ruin probability), 4 LLM features with graceful degradation (sandboxed text-to-SQL chat), documented security rewrite (WebAuthn, CSRF, CSP).
decisioni & tradeoffdecisions & tradeoffs
Feature LLM dietro circuit breaker: la piattaforma resta pienamente utilizzabile con l'LLM giù — degradazione pianificata, non best-effort.LLM features behind a circuit breaker: the platform stays fully usable with the LLM down — planned degradation, not best-effort.
Chat text-to-SQL sandboxed: l'LLM non tocca il database direttamente — query validate in sandbox. La capability senza la superficie d'attacco.Sandboxed text-to-SQL chat: the LLM never touches the database directly — queries go through validation in a sandbox. The capability without the attack surface.
Security rewrite (WebAuthn, CSRF, CSP) su un'app già in uso: retrofit trattato come progetto — scope e verifiche documentate — non come patch.Security rewrite (WebAuthn, CSRF, CSP) on an app already in use: retrofit run as a project — documented scope and verification — not as a patch.
Servizio condiviso di browser-automation engine-pluggable: 6 backend di rendering dietro un'unica API con fallback a caldo, motore anti-bot YAML-driven (8 segnali, 31 predicati), sessioni "human-shaped" — consumato da 3+ progetti.Shared engine-pluggable browser-automation service: 6 rendering backends behind one API with hot fallback, YAML-driven anti-bot engine (8 signals, 31 predicates), human-shaped sessions — consumed by 3+ projects.
6 engine6 enginesinfra condivisashared infra
IoT & Device FleetIoT & Device Fleet
produzioneproduction
Flotta di 60+ device IoT gestita end-to-end con 100+ automazioni event-driven: telemetria continua, health-check con rollback automatico sugli update, deploy su hardware self-hosted (mini-server x86, nodo ARM64 di riserva); hub di geolocation & asset-tracking GPS/BLE con 14 job schedulati.Fleet of 60+ IoT devices managed end-to-end with 100+ event-driven automations: continuous telemetry, health checks with automatic rollback on updates, deployment on self-hosted hardware (x86 mini-server, ARM64 standby node); GPS/BLE geolocation & asset-tracking hub with 14 scheduled jobs.
decisioni & tradeoffdecisions & tradeoffs
Update della flotta dietro health-gate con rollback automatico: nessun update manuale, ma nessun update cieco — se un servizio non torna sano, torna da solo alla versione precedente.Fleet updates behind a health gate with automatic rollback: no manual updates, but no blind updates either — if a service doesn't come back healthy, it rolls back on its own.
Scala personale dichiarata, ciclo di vita aziendale: provisioning, telemetria, update sicuri e incident response sono gli stessi di una flotta enterprise — cambia il numero di device, non il metodo.Personal scale, declared openly — enterprise lifecycle: provisioning, telemetry, safe updates and incident response are the same as in an enterprise fleet; the device count changes, not the method.
Geolocation self-hosted: i dati di posizione non lasciano l'infrastruttura — la capability dell'asset-tracking senza cedere dati a un cloud terzo.Self-hosted geolocation: location data never leaves the infrastructure — asset-tracking capability without handing data to a third-party cloud.
$ ls ~/systems/ ·e inoltre:also:sistema esperto bayesiano (fisiologia) · observability per inference AI locale · monitoring & alerting event-driven.Bayesian expert system (physiology) · observability for local AI inference · event-driven monitoring & alerting.
04// Architetture// Architecture
ArchitettureArchitecture
Come funzionano i sistemi di punta — clicca un pannello per aprire il diagramma.How the flagship systems work — click a panel to open the diagram.
Personal AI Knowledge System — retrieval ibrido + brainPersonal AI Knowledge System — hybrid retrieval + brain+
Tre lane di retrieval fuse via RRF, poi un brain con confidence-routing e critic anti-contraddizione verso 5 canali di output.Three retrieval lanes fused via RRF, then a brain with confidence-routing and an anti-contradiction critic feeding 5 output channels.
Collector isolati sul nodo egress, consegna crash-safe via WAL al nodo always-on, analisi LLM e hand-off al knowledge graph.Collectors isolated on the egress node, crash-safe WAL delivery to the always-on node, LLM analysis and hand-off into the knowledge graph.
Resale-Intelligence Platform — qualificazione a convergenzaResale-Intelligence Platform — convergence qualification+
Estrazione distribuita → filtro → qualificazione vision multi-provider con failover → pricing → scorer a convergenza di 6 segnali.Distributed extraction → filtering → multi-provider vision qualification with failover → pricing → 6-signal convergence scorer.
05// Competenze// Skills
CompetenzeSkills
Dove governance e delivery tecnica si incontrano.Where governance and technical delivery meet.
