Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I'm Luca Zilli, a ML engineer and data scientist. I collaborate with startups and research teams to build robust ML pipelines, information retrieval solutions, and back-end features. My background spans physics, quantum computing, Machine learning and software development. I have contributed to open-source projects (e.g., Qibo), co-founded a startup, and developed AI features for MVPs. I thrive at the intersection of research and product, shipping end-to-end ML solutions from data collection to deployment. My stack: aws, docker, Node.js, aws, databricks, dynamoDB, postgres, sagemaker, pyspark, anaconda, azure, opensearch, django, nest.js, sentence-transfomers.…I'm Luca Zilli, a ML engineer and data scientist. I collaborate with startups and research teams to build robust ML pipelines, information retrieval solutions, and back-end features. My background spans physics, quantum computing, Machine learning and software development. I have contributed to open-source projects (e.g., Qibo), co-founded a startup, and developed AI features for MVPs. I thrive at the intersection of research and product, shipping end-to-end ML solutions from data collection to deployment. My stack: aws, docker, Node.js, aws, databricks, dynamoDB, postgres, sagemaker, pyspark, anaconda, azure, opensearch, django, nest.js, sentence-transfomers.

Luca Zilli





I'm Luca Zilli, a ML engineer and data scientist. I collaborate with startups and research teams to build robust ML pipelines, information retrieval solutions, and back-end features. My background spans physics, quantum computing, Machine learning and software development. I have contributed to open-source projects (e.g., Qibo), co-founded a startup, and developed AI features for MVPs. I thrive at the intersection of research and product, shipping end-to-end ML solutions from data collection to deployment. My stack: aws, docker, Node.js, aws, databricks, dynamoDB, postgres, sagemaker, pyspark, anaconda, azure, opensearch, django, nest.js, sentence-transfomers.…I'm Luca Zilli, a ML engineer and data scientist. I collaborate with startups and research teams to build robust ML pipelines, information retrieval solutions, and back-end features. My background spans physics, quantum computing, Machine learning and software development. I have contributed to open-source projects (e.g., Qibo), co-founded a startup, and developed AI features for MVPs. I thrive at the intersection of research and product, shipping end-to-end ML solutions from data collection to deployment. My stack: aws, docker, Node.js, aws, databricks, dynamoDB, postgres, sagemaker, pyspark, anaconda, azure, opensearch, django, nest.js, sentence-transfomers.

Available to hire

I’m Luca Zilli, a ML engineer and data scientist. I collaborate with startups and research teams to build robust ML pipelines, information retrieval solutions, and back-end features.

My background spans physics, quantum computing, Machine learning and software development. I have contributed to open-source projects (e.g., Qibo), co-founded a startup, and developed AI features for MVPs. I thrive at the intersection of research and product, shipping end-to-end ML solutions from data collection to deployment.

My stack: aws, docker, Node.js, aws, databricks, dynamoDB, postgres, sagemaker, pyspark, anaconda, azure,
opensearch, django, nest.js, sentence-transfomers.

Skills

Experience Level

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Beginner

Beginner

Language

Italian

Fluent

English

Fluent

Work Experience

Machine Learning Engineer at Source (startup)

June 1, 2024 - Present

NLP-focused ML engineer: developed a scraping pipeline with Scrapy; reviewed literature and designed strategies for information retrieval (BM25, hybrid search, reranking); built, maintained and improved email-parsing agents; created a dataset to evaluate AI agent flows; trained sentence-transformers and cross-encoders for reranking; deployed ML models on AWS; built ETL pipelines with PySpark and Databricks; added backend features in Django and Nest.js. Stack included AWS, Docker, Node.js, Python, TypeScript, Postgres, Databricks, Django, Nest.js, OpenSearch, DynamoDB.

Data Scientist at Strobilo

February 1, 2024 - June 1, 2024

Product-focused data scientist for a SaaS startup. Reviewed literature and developed both first-principle and black-box models; main research area included virus risk assessment and thermal comfort modelling.

Tech Lead and co-founder at Suppai

September 1, 2023 - February 1, 2024

Co-founded and led early-stage activities: sales, fundraising, MVP development. Selected for the Berkeley SkyDeck accelerator batch 17. Managed cloud architecture (AWS, Azure) with the CTO. Shaped AI strategy for the MVP and developed OCR-based API to read invoices.

Qubit Developer and Researcher at Qibo (Open Source Project)

October 1, 2022 - March 1, 2023

Contributed to Qibo, an open-source framework for controlling and simulating quantum computers. Developed a noise model for digital quantum devices, researched state-of-the-art models, implemented and validated the best models, and extended the model to include idle qubits.

Internship Manager at EasyTap

June 1, 2021 - August 1, 2021

Managed a group of five interns alongside the CEO to build a business digital card application; coordinated project tasks and timelines.

Researcher at University of Milan

April 1, 2020 - December 1, 2020

Developed ML algorithms to forecast energy unbalances in the Italian power grid (Terna S.p.A.); explored RNN-based approaches and chaos-theory-inspired methods for time-series forecasting.