From demo to production.
AI that runs.
Models that ship,
not just notebooks.
Pipelines that don't
wake you at 3 a.m.
Warehouses
turned into decisions.
Platforms for the
boring quarter.
About
I take AI from notebook demos to systems that run.
The hard part of applied AI isn't the model. It's the integration: stable orchestration, eval gates that fire before users notice, guardrails that hold, latency budgets that don't blow up the finance review.
Data Scientist who ships models, not notebooks.
Boring stack first — gradient boosting, classical NLP, embeddings. Deep learning only when it's the cheapest answer. Forecasts come with calibrated confidence intervals.
Pipelines that don't wake you at 3 a.m.
Bronze/silver/gold on Databricks + ADF with proper SLAs; validation, secret scanning, trigger gates on every PR; dbt with tests and lineage; IaC from day one.
Warehouses turned into decisions.
The hardest part of BI is the semantic model. Power BI semantic models executives can trust, DAX tuned with VertiPaq Analyzer, governance that scales.
I lead with: "who pages whom at 3 a.m.?"
End-to-end platform design on Azure with governance, lineage, FinOps baked in from day one — not bolted on in year two.
— "Thoughtful before fancy."
What I do — in detail
Models that survive contact with humans
Star and snowflake where they fit. Data vault when history matters. Contracts at every boundary so producers can refactor without breaking downstream.
Lakehouse, lambda, kappa — choosing what fits
Event-driven where it earns complexity. Batch where SLAs allow. Cost-aware always.
Boring stack first, deep learning when it pays
Gradient boosting, classical NLP, well-engineered features. Foundation models go through eval gates before they touch users.
Forecasts that respect the process
Seasonality, regime shifts, exogenous shocks. Calibrated confidence intervals. Causal methods when the question demands them.
The work that decides payback or drift
Contracts at boundaries. Lineage that survives refactor. Drift detection. Cost dashboards someone outside engineering reads.
Experience — themes
Around a decade across data engineering and applied AI in Italy and the EU.
AI integration architect · freelance
Production LLM systems and AI agents on Azure. Edge AI on Foundry Local; CI/CD for ADF.
Senior data engineer · Azure data platforms
Lakehouse design — bronze/silver/gold on Databricks + ADF, dbt, CI/CD, cost optimization.
Data & BI consultant · DsBiConsultant + freelance
Enterprise reporting in banking, insurance, media, retail. SQL Server modernization, Power BI semantic models.
Digital humanities · Università di Pisa
Network analysis, NLP on historical corpora, graph DBs for cultural heritage.
Software & web · early career
Full-stack — PHP, JavaScript, Linux, MongoDB, early Docker.
Stack
- AI / ML
- Azure AI Foundry · OpenAI · LangChain · PromptFlow · MLflow · Foundry Local · ONNX
- Data
- Azure Data Factory · Databricks · Synapse · Fabric · SQL Server · Spark · dbt · Neo4j
- Platform
- Azure · Terraform · Bicep · GitHub Actions · Docker
- Languages
- Python · PowerShell · TypeScript · SQL
- Spoken
- Italian · English · Persian
Featured work
⚡ sqlsnapshot
Open-source PowerShell tool — your SQL Server, x-rayed in one command.
→ github.com/mojiTMJ/sqlsnapshot🛡️ ADF CI/CD that catches secrets
GitHub Actions workflow for Azure Data Factory.
→ ADF · CI/CD📜 Italian Academies as a graph
175 years of Italian academies as a property graph in Neo4j.
→ Neo4j🧠 Edge LLM proofs
Running 7B-parameter models on a Surface laptop with Azure AI Foundry Local.
→ writeup in progressEngage me for
- Taking an LLM demo to production
- AI agents that don't get jailbroken in week two
- Edge AI PoCs · Foundry Local · ONNX
- AI evaluation pipelines — drift, regression gates
- CI/CD & governance for data under AI
- Forecasting with calibrated intervals
- Causal inference for attribution / treatment
- Recommendation / ranking models
- Evaluation frameworks for foundation models
- NLP pipelines for Italian corpora
- Greenfield lakehouse design
- SSIS / on-prem warehouses → Azure
- CI/CD maturity on ADF estates
- dbt rollouts with tests & contracts
- Streaming pipelines · Kafka / Event Hubs
- Power BI rescues — slow, wrong, ungoverned
- Semantic model redesign
- DAX optimization · VertiPaq
- Cognos / SSRS / OBIEE → Power BI
- Training your BI team
- End-to-end Azure platform design
- Architecture review / RFP second-opinion
- Governance rollouts
- Migration roadmaps
- FinOps in architecture
Contact
Tell me about the problem. One-line briefs welcome. I reply within 24h.