Davide Palleschi

AI Engineer & Full Stack Developer.
Building intelligent systems that bridge the gap between research and reality.

About Me

I am an AI Engineer currently working at DeepPlants, with a specific focus on Generative AI and Large Language Models (LLMs). My professional approach covers the entire lifecycle of AI development: from the research-heavy side of Fine-Tuning models to the architectural challenge of building autonomous Agentic Systems.

I hold a Master’s Degree in Artificial Intelligence and Robotics, with a thesis titled "Privacy-oriented Object Detection: Detecting People and Actions in Low-Resolution Images". While my academic roots are in Computer Vision and YOLOv8, I have successfully transitioned my engineering mindset to NLP, applying rigorous testing to model reasoning.

My technical expertise centers on Python, PyTorch, and Hugging Face. I specialize in optimizing models using LoRA/PEFT techniques and orchestrating complex, tool-using agents with LangGraph and LangChain. I excel in creating evaluation pipelines to measure model reliability and ensure robust performance.

Beyond professional work, I am interested in IoT and smart home technologies, exploring how AI can interact with the physical world.

Technical Arsenal

A comprehensive toolkit for building intelligent, scalable systems.

AI & ML

Python
PyTorch
Hugging Face
LLMs
RAG
LangChain
YOLO
Computer Vision
Fine-Tuning
LoRA/PEFT

Full Stack

Next.js
React
TypeScript
Tailwind CSS
Node.js
PostgreSQL
Framer Motion

DevOps & Tools

Docker
Git
Linux
AWS
CI/CD
VS Code

Embedded & IoT

C++
Arduino
ESP32
Home Assistant
MQTT
PCB Design

Featured Projects

A collection of my work in AI, IoT, and Full Stack Development.

Zepp2Hass
Personal

Zepp2Hass

2025-11 - Present

A custom Home Assistant integration and Zepp OS app to sync smartwatch data in real-time.

Home Assistant
Zepp OS
Python
+2
WebSearch AI
Personal

WebSearch AI

2025-11 - 2025-11

A modular Python library for semantic web search with LLM summarization.

Open Source
Python Library
Search
+1
Cabbo
Work

Cabbo

2025-07 - 2025-10

An advanced agricultural AI platform orchestrating specialized agents for decision support.

AI Engineering
Multi-Agent Systems
FastAPI
+1
Agricultural RAG Systems
Work

Agricultural RAG Systems

2025-04 - 2025-05

Advanced RAG pipelines using Qdrant and Qwen3 to make agricultural knowledge accessible to AI.

RAG
Vector DB
Qdrant
+2
CABBAGE (AgriBench)
Work

CABBAGE (AgriBench)

2024-11 - 2025-02

A comprehensive multimodal benchmark (74K+ questions) for agricultural AI.

NeurIPS 2025
AI Research
Benchmark
+1
Privacy-oriented Object Detection
University

Privacy-oriented Object Detection

2023-10 - 2024-05

Detecting people and actions in low-resolution images for privacy-preserving surveillance.

Computer Vision
YOLOv8
Privacy
+1
Omnisensor
Personal

Omnisensor

2022-11 - 2023-03

A DIY device for presence detection and monitoring environmental conditions.

IoT
Electronics
ESP32
+2
The Maze Game
University

The Maze Game

2021-07 - 2021-09

A university project utilizing WebGL to create a 3D maze escape game.

WebGL
Game Dev
3D Graphics
+1
Smart Home
Personal

Smart Home

2016-06 - Present

My Smart home, developed since 2016, featuring over 100 devices and complex automations.

Home Assistant
Node-RED
Zigbee
+2

Get in Touch

Interested in collaborating on AI projects or have a question? Feel free to reach out.