Valerio Valente, portrait

Valerio Valente.

I build AI systems that survive contact with reality.

If your idea of fun is digging into the messy details instead of waving hands at slide decks, we are already friends. I spend most of my time turning data and machine learning into things that actually work outside a Jupyter notebook, which is where most "AI" quietly goes to die.

When I am not doing that, I am either outside pretending I have a balanced life, reading something I cannot put down, or deep into a manga binge I will regret the next morning. I also bake sourdough, which is controlled fermentation dressed up as a hobby.

Experience

Where I have worked, in reverse order.

  1. 2025 · now

    Data Scientist InSilicoTrials Technologies

    Synthetic data generation, agentic systems built on the Model Context Protocol, explainable AI, and Azure deployments. I also help turn rough ideas from clients into POCs that actually run.

  2. 2024 · 2025

    Junior Data Scientist InSilicoTrials Technologies

    Trained and shipped models on clinical data, wrote internal Python packages that took friction out of day-to-day ML work, and ran coding interviews and onboarding for new data scientists.

  3. 2023 · 2024

    Junior Data Scientist Miraitek

    RAG pipelines on AWS, anomaly-detection algorithms for industrial signals, and BI dashboards driven by SQL for manufacturing analytics.

Selected Projects

A few things I am proudest of.

  1. 2025

    LLM multi-agent systems

    Designed and contributed to several LLM systems, including a multi-agent setup with a Model Context Protocol server exposing specialised tools. Contributed upstream to the open-source mcpadapt library. (Model Context Protocol , mcpadapt )

  2. 2024

    FDA challenge, top-5 finish

    Placed in the top five of an FDA precisionFDA challenge, representing my company on a RAG solution evaluated against regulatory standards. (Challenge results )

  3. 2024

    POC studio

    Built end-to-end proofs of concept for clients across manufacturing and life sciences. Most of the work was translating vague problem statements into minimum viable products that stakeholders could actually click on.

Side Quests

The hobbies are load-bearing.

Sourdough
Controlled fermentation dressed up as a hobby. Bread, pizza, anything involving yeast: irrationally into it.
Reading
Usually mid-book on something I can't put down. The current rotation lives on the reading shelf.
Manga
Occasional deep dives I will regret the next morning, and recommend the morning after that.
Outdoors
Pretending I have a balanced life. Hiking, long walks, anywhere with a view.

Certifications & Awards

Receipts.

  1. Aug 2024

    Deploying Machine Learning Models in Production DeepLearning.AI

    OC06EOAHREQU

  2. Aug 2024

    Introduction to Retrieval Augmented Generation Duke University

    UT2G2PAI109

  3. May 2024

    Machine Learning in Production DeepLearning.AI

    96CN9B7M28XA

  4. Nov 2021

    Huawei Seeds For The Future, finalist Huawei

    Read the article

Hello

Say hi, share a draft, suggest a book.

The fastest reply paths are the social ones below. The form is fine too if a longer note is easier. Either way, I read everything.

Contact form