Freelance · P.IVA · Milano / Forlì

AI & Software Engineer
building real things with LLMs.

I help companies and startups ship production-grade AI features — NLP pipelines, RAG systems, LLM integrations and the backend that makes them work in the real world.

  • 📍 Milan, Italy
  • 🎓 M.S. CS @ Politecnico di Milano
  • 💼 Available for projects

Services

What I can build for you

🧠

LLM & NLP Integrations

Custom integrations with OpenAI, Anthropic, open-source models. Prompt engineering, function calling, structured outputs and evals.

  • OpenAI
  • Anthropic
  • HuggingFace
  • LangChain
📚

RAG Systems

End-to-end Retrieval-Augmented Generation pipelines — ingestion, chunking, embeddings, vector DBs and answer evaluation.

  • Vector DBs
  • Embeddings
  • LlamaIndex
  • Evals
⚙️

Backend & APIs

Production-ready Python and Java backends. FastAPI services, PostgreSQL, Docker deployments — built lean, no over-engineering.

  • FastAPI
  • Spring Boot
  • PostgreSQL
  • Docker
🔁

AI Automation (n8n)

Workflow automation for SMEs combining n8n, LLMs and external APIs. Replace repetitive ops work with reliable pipelines.

  • n8n
  • Webhooks
  • Zapier
  • Make
📊

ML Engineering

Custom models for classification, time-series and computer vision. From dataset cleaning to deployment, with proper evaluation.

  • PyTorch
  • scikit-learn
  • Transfer Learning
  • MLOps
🧪

Technical Consulting

Code reviews, architecture audits, AI-readiness assessments. Honest feedback on what to build, what to buy and what to drop.

  • Audits
  • Architecture
  • Code Review

Selected work

Portfolio

A selection of recent projects across data engineering, computer vision and deep learning.

Dec 2025 – Jan 2026 Data Engineering

Global Shark Attacks — Data Quality Pipeline

End-to-end data cleaning, quality assessment and enrichment pipeline on a real-world messy dataset. Fuzzy record linkage, schema validation and quality scoring across 6,000+ records.

  • Python
  • Pandas
  • DIQ
  • Record Linkage
↗ View on GitHub
Dec 2025 Computer Vision

Histopathology Image Classification

Breast cancer tissue classification using fine-tuned EfficientNet, ResNet and Vision Transformer (ViT). Applied Grad-CAM for model interpretability. Final score 4.5/5.

  • PyTorch
  • Transfer Learning
  • ViT
  • Grad-CAM
↗ View on GitHub
Nov 2025 Deep Learning

Multivariate Time-Series Classification

BiLSTM / Conv1D / GRU ensemble with attention mechanisms for sequence modelling. Achieved 95.5% F1 on the AN2DL competition. Team "ReLUminatii".

  • PyTorch
  • BiLSTM
  • Attention
  • Ensemble
↗ View on GitHub

More on github.com/dvsnshk

About

Hi, I'm Devis 👋🏼

I'm a Computer Science master's student at Politecnico di Milano, specialising in AI/ML, NLP and Edge AI. Alongside my studies I work as a freelance AI & Software Engineer, helping companies turn LLM ideas into production systems that actually ship.

My background blends academic depth (3.7/4.0 GPA, 4 lodi) with hands-on engineering experience: I spent 7 months at Sensei Srl building an applicant tracking system backend with Java Spring Boot, Apache Lucene and PostgreSQL — full-text search, CV processing, real production constraints.

I work best on lean, well-scoped projects where outcomes matter more than buzzwords. If that sounds like you, let's talk.

AI / ML

  • PyTorch
  • TensorFlow
  • LLMs
  • RAG
  • NLP
  • scikit-learn
  • LangChain
  • HuggingFace

Backend & Data

  • Python
  • FastAPI
  • Java
  • Spring
  • PostgreSQL
  • Apache Kafka
  • ElasticSearch
  • Vector DBs
  • Docker
  • Git

Get in touch

Let's build something.

Reach out for freelance work, collaborations, or just to say hi. I usually reply within 24 hours.