root@hub:~/cv$ man ludovico_de_salvo

[cd ..]
[ ADMIN ]

LUDOVICO DE SALVO

AI Engineer

SYS.LOC: Rome, ItalySYS.MAIL: ludovicodesalvo@proton.meSYS.NET: linkedin.com/in/ludovicodesalvoSYS.REPO: github.com/LudovicoDeSalvo
uid=0000

## ABOUT_ME

AI Engineer building LLM and optimization systems for real business use. At a fire-safety SME I built a RAG assistant, a time-window route-planning heuristic for field technicians, and the Odoo tooling the company runs on, while owning all of its IT infrastructure. M.Sc. AI & Robotics (Sapienza, exp. 2027) built on a Management Engineering foundation: models that solve business problems, not just benchmarks.

## TOP_SKILLS

LLMs & RAGMachine LearningDeep LearningReinforcement LearningComputer VisionPyTorch

## EXPERIENCE

AI Engineer

[ Jul 2026 - Present ]
Gallelli Antincendio SRL, Rome, Italy
  • Sole IT and engineering function for a 19-person fire-safety company running on Odoo 19.
  • Built a RAG customer assistant for a group company: heading-aware chunking of Markdown docs, Mistral embeddings in PostgreSQL/pgvector, hybrid vector + keyword retrieval, cited answers from Mistral Large via FastAPI (EU-hosted).
  • Designed the route-planning engine of a field-technician tablet app in Odoo: cheapest insertion, 2-opt/Or-opt and ruin-and-recreate, with opening-hour time windows, service and waiting times. Google Maps supplies only drive times.
  • Built custom Odoo modules (JS) for on-site job capture (timings, measurements, photos), logistics tools, and a shared email frontend that turns emails into Odoo records. Leading the migration to Odoo.sh.
  • Run all IT: servers and self-hosted services, network and security, email and domains, workstations and helpdesk, satellite fleet-tracking rollout.

Full-Stack Developer (Volunteer)

[ Jul 2026 - Present ]
Fondazione Magna Graecia ETS, fondazionemagnagraecia.it
  • Sole developer of the foundation’s live website: Next.js 16 (App Router, React 19, strict TypeScript), Tailwind CSS 4, Payload CMS 3 on PostgreSQL 17.
  • Run the VPS end to end: Docker deploys via Coolify behind Traefik (TLS), backups, security updates, email and DNS, CMS content management.

## PROJECTS

Bio-Adaptive Music Engine (BAME): Closed-Loop RL System
  • Developed a Deep Reinforcement Learning framework designed to regulate human physiological states (arousal/stress) through music.
  • Treated human physiology as a control problem, engineering a proprietary 'World Model' to simulate biological reactions.
  • Trained an agent to optimize physiological outcomes without real-time human risk.
End-to-End License Plate Recognition Pipeline
  • Engineered a modular pipeline for real-time license plate detection and recognition on the CCPD2019 dataset.
  • Orchestrated a full end-to-end workflow: Data ingestion -> YOLOv Detection -> Cropping/Alignment -> Recognition -> Inference.
  • Implemented and compared a baseline CNN+LSTM+CTC against a Transformer-based PDLPR (Parallel Decoder) model.
OCR Post-Correction with Fine-Tuned LLMs
  • Developed a portable pipeline to correct noisy OCR text outputs using Parameter-Efficient Fine-Tuning (PEFT) on LLMs.
  • Implemented LoRA and 8-bit quantization to fine-tune Llama and Minerva models on consumer hardware.
  • Designed an 'LLM-as-a-Judge' automated evaluation system using the Gemini API, validated against human scoring via correlation analysis.
./VIEW_ALL_PROJECTS.sh

## EDUCATION

Master Student in Artificial Intelligence & Robotics

[ 2024 - Jul 2027 (expected) ]
Sapienza University, Rome, Italy

English Master Degree. Relevant already completed courseworks: Machine Learning, Deep Learning, Computer Vision, Reinforcement Learning, Neural Networks, Multilingual Natural Language Processing (MNLP).

Bachelor Degree in Management Engineering (L-8)

[ 2017 - 2024 ]
Università della Calabria, Italy

## DETAILED_SKILLS

> Concepts

Artificial IntelligenceDeep LearningReinforcement LearningComputer VisionNatural Language Processing (NLP)Neural NetworksLarge Language Models (LLM)Retrieval-Augmented Generation (RAG)Hybrid SearchCombinatorial Optimization (VRP heuristics)Convolutional Neural Networks (CNN)Long Short-Term Memory (LSTM)Transformer ModelsLLM fine-tuning

> Tools & Systems

LinuxDockerPostgreSQLCoolifyTraefikGitCLIJupyterRobot Operating System (ROS)KatharaMicrosoft Office (Word, Excel, PowerPoint)Android (ADB, Custom ROMs, Fastboot)PC Building & Hardware Assembly

> Languages

PythonJavaC++TypeScriptJavaScriptMATLABHTMLCSSPlanning Domain Definition Language (PDDL)

> Frameworks & Libs

PyTorchNumPyMatplotlibOpenCVYOLOFAISSpgvectorFastAPIMistral AIMERTOpenAI GymGoogle GeminiOdooNext.jsTailwind CSSPayload CMSFirebase

## LANGUAGES

Italian:Native (C2 level)
English:Full Professional proficiency (C1 level with IELTS certification)
// EOF: Ludovico_De_Salvo.md
LDSroot@hub:~/cv