/ work

Selected work,
across four years.

A curated selection of production systems, open-source models, and applied research. Most client work is under NDA — described here with anonymized details and verifiable outcomes.

8M+
end users served
2M+
MAU on flagship system
99.9%
uptime across live systems
4+
systems live in production
CASE STUDYAI · agents · cloudlive

Cloud-native news chatbot

Real-time news summarization for one of Italy's major digital outlets. Multi-agent architecture with persistent memory, streaming responses, and semantic retrieval over a live corpus.

2M+
monthly active users
<180ms
avg response latency
99.9%
uptime SLA
live
real-time news corpus
clientmajor IT news outlet
rolelead engineer
year2025
durationongoing
typeclient work
LlamaIndexPythonAWS LambdaFastAPIRedisPostgreSQLDockerGitHub Actions
Read the full case study →
01Selected projects

client engagements and applied work

sort: most recent ↓
LLM · computer visionlive
CAD parts vision classifier

LLM-powered computer vision classifier for automatic CAD parts recognition. Streamlines design workflows for an industrial client by automating part identification and metadata enrichment.

→ Streamlined design workflow · accuracy uplift
Vision LLMsPythonFastAPIDocker
clientindustrial B2B
rolesolo consultant
year2025
typeclient work
LLM · document intelligencelive
Receipt & document scanner

LLM-powered scanning system for receipts and invoices. Enables semantic search across large archives and automated structured data extraction for finance teams.

→ Semantic search · automated data extraction
LangChainOCRPostgreSQLFastAPI
clientSaaS B2B
rolelead engineer
year2025
typeclient work
AI · agents · personallive
LorenzoBot

Cloud-native AI assistant integrated into this website. Provides accurate, context-aware information about my work using multi-agent reasoning, persistent memory, and Gemini/LLM orchestration.

→ Powering the chat on lorenzomaiuri.dev
LangChainGeminiNext.jsVector store
clientself
rolesolo
year2025
typepersonal
NLP · fine-tuninglive
BERT GDPR classifier

Fine-tuned BERT for personal data detection, deployed into a B2B production platform.

→ 85% accuracy · 90% less review time
PyTorchBERTHuggingFace.NET
clientPharmaidea SRL
rolelead engineer
year2024
typeclient work
Data · infradelivered
Data warehouse modernization

Oracle → PostgreSQL migration with full ETL rewrite on Airflow and CI/CD pipeline.

→ 100% cost reduction · 20% faster queries
PostgreSQLOracleAirflowDocker
clientPharmaidea SRL
rolelead engineer
year2024
typeclient work
ML · ops dashboarddelivered
Logistics anomaly dashboard

Real-time cost control dashboard for logistics operations with ML-based anomaly detection on shipment data. Surfaces outliers and pricing irregularities automatically.

→ 70% reduction in manual checking time
Pythonscikit-learnPowerBIPostgreSQL
clientPharmaidea SRL
rolelead engineer
year2023
typeclient work
ML · prioritizationdelivered
Order prioritization engine

ML-based prioritization system integrated into a B2B platform. Ranks incoming orders by urgency and downstream impact, accelerating processing for time-critical requests.

→ 20% faster processing for critical orders
scikit-learnPython.NET
clientPharmaidea SRL
rolesoftware engineer
year2023
typeclient work
CV · open sourcedelivered
Histopathologic cancer CNN

Deep learning classifier for metastatic tissue in lymph node scans. Public on HuggingFace.

→ Published · HuggingFace Hub
PyTorchCNNKaggle
roleauthor
year2025
typeopen source
LLM · generativedelivered
DanteGPT

GPT-2 fine-tuned on Divina Commedia to generate text in Dante's poetic style and themes.

→ Open model · HuggingFace
GPT-2fine-tuningHuggingFace
roleauthor
year2024
typeopen source
02Open models & research

published on HuggingFace Hub

Want a similar project?

Let's see if I'm a fit.

Most of these projects started with a 30-min technical chat. Bring your problem, your stack, and your constraints — I'll come prepared.