London, United Kingdom

Oscar de Francesca

Software Engineer · Systems & ML

Bloomberg·MSc CS, EPFL·Incoming: ETH Zurich research

I work across systems and machine learning. Right now I'm building real-time C++ infrastructure at Bloomberg in London. I'm completing an MSc in Computer Science at EPFL, and from October I'll be doing my EPFL Master's thesis, hosted at ETH Zurich, on diffusion language models for antibody design.

View Projects About Me

Worked & Studied With

Experience

View all

Master's Thesis (Incoming)

·ETH Zurich

Oct 2026 – Apr 2027 · Basel, Switzerland

Software Engineer

·Bloomberg

Mar 2026 – Oct 2026 · London, United Kingdom

Data Science Intern

·Researchable

Jun 2023 – Sep 2023 · Groningen, Netherlands

Teaching Assistant

·University of Groningen

Apr 2023 – Jul 2024 · Groningen, Netherlands

Software Engineering Intern

·ASML

Feb 2023 – Sep 2023 · Veldhoven, Netherlands

Blockchain Engineering Intern

·Securrency

Jul 2022 – Aug 2022 · Abu Dhabi, UAE

Featured Projects

View all

FeaturedEPFL

OptiFlow: AI-Enhanced Retail Inventory Monitoring

November 2025 · school

Built an AI-enhanced system combining wearable RFID scanning with UWB indoor positioning for Decathlon, enabling real-time shelf-level inventory monitoring and store flow optimization.

systemsmlembeddedweb

Medical LLM architecture and training pipeline

FeaturedEPFL

LLMs from Scratch & Medical Fine-Tuning

June 2025 · school

Implemented a GPT-2 architecture from scratch in PyTorch, then fine-tuned Mistral models on medical conversational and MCQ datasets using LoRA for clinical question answering.

mlllmnlp

Solar irradiance probabilistic forecast visualization

FeaturedEPFL CFI Lab

Uncertainty-Aware Solar Forecasting

December 2024 · school

Developed probabilistic solar irradiance forecasting models using quantile regression and Bayesian neural networks, producing calibrated 95% prediction intervals from webcam imagery and meteorological data.

mlprobabilisticforecasting

FeaturedUniversity of Groningen

AI Research Management Platform

July 2024 · school

Designed and built LLACE, a full-stack platform for managing the lifecycle of AI models in healthcare research, from project organization and model versioning to deployment, built in collaboration with UMCG.

webbackend

Education

MSc Computer Science

EPFL · 2024 – 2027

In progress, 5.38/6 average, with a minor in Management, Technology & Entrepreneurship. Coursework across distributed systems, security, and machine learning. Master's thesis hosted at ETH Zurich from October 2026.

BSc Computer Science

University of Groningen · 2021 – 2024

Cum Laude, 8.6/10 average, Honours College. Coursework in algorithms, operating systems, concurrent programming, and data systems.

Skills & Tools

Languages

C++PythonCJavaSQLBashHaskellRAssembly

Systems

Low-latencyConcurrencyDistributed systemsReal-timePOSIX / Unix

ML & AI

PyTorchHugging FaceLoRA / PEFTDeepSpeedNumPypandasscikit-learn

Backend & Tools

KafkaLinuxDockerPostgreSQLFastAPICMakeGitCI/CD

Get in touch

I'm open to conversations about systems, machine learning, and interesting engineering problems. Email is the best way to reach me.

Email Me LinkedIn GitHub

oscar.defrancesca@gmail.com