🧠
LLM & NLP Integrations
Custom integrations with OpenAI, Anthropic, open-source models. Prompt engineering, function calling, structured outputs and evals.
Freelance · P.IVA
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.
Services
What I can build for you
📚
RAG Systems
End-to-end Retrieval-Augmented Generation pipelines — ingestion, chunking, embeddings, vector DBs and answer evaluation.
⚙️
Backend & APIs
Production-ready Python and Java backends. FastAPI services, PostgreSQL, Docker deployments — built lean, no over-engineering.
🔁
AI Automation (n8n)
Workflow automation for SMEs combining n8n, LLMs and external APIs. Replace repetitive ops work with reliable pipelines.
📊
ML Engineering
Custom models for classification, time-series and computer vision. From dataset cleaning to deployment, with proper evaluation.
🧪
Technical Consulting
Code reviews, architecture audits, AI-readiness assessments. Honest feedback on what to build, what to buy and what to drop.
Selected work
Portfolio
A selection of recent projects across data engineering, computer vision and deep learning.
Continuous LSTM & cPNN in CapyMOA
Native integration of Continuous LSTM (cLSTM) and continuous Progressive Neural Networks (cPNN) as classifiers inside the CapyMOA streaming framework. Anytime inference with sliding windows and dynamic column expansion for concept drift.
- PyTorch
- CapyMOA
- cLSTM
- cPNN
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
- NumPy
- ydata-profiling
Histopathology Image Classification
Breast cancer tissue classification using fine-tuned EfficientNet, ResNet and Vision Transformer (ViT). Applied Grad-CAM for model interpretability.
- PyTorch
- Transfer Learning
- ViT
- Fine-Tuning
Multivariate Time-Series Classification
BiLSTM / Conv1D / GRU ensemble with attention mechanisms for sequence modelling. Achieved 95.5% F1 on the AN2DL competition.
- PyTorch
- BiLSTM
- Attention
- GRU
More on github.com/devisnsk
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 AI ideas into production systems that actually ship.
AI / ML
- PyTorch
- TensorFlow
- LLMs
- RAG
- NLP
- scikit-learn
- LangChain
- n8n
- 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.