Tomás Erdmannsdörffer
CV

The average adult heart, from CT scans (Rodero et al. 2021). 52 bpm

I teach physics to neural networks.

I’m Tomás, an ML engineer in Santiago, Chile. I build physics-informed neural networks for heart mechanics, and compressed versions that still get the answer right.

See the demos Read the CV

A heart is a pumpmade of fibres.

Its muscle cells run in sheets that wind around the ventricles. When they shorten together the wall thickens, the base pulls down toward the apex and the whole organ wrings itself out. The light that crosses it before each beat is the electrical wave that sets it off.

Engraving of three hearts with their great vessels, the muscle fibres drawn across their surfaces
Richard Lower drew the fibres on the surface of the heart in 1669, in Tractatus de Corde. Wellcome Collection, CC BY 4.0.

+60° inside,−60° outside.

Through the thickness of the wall the fibre angle turns by about 120 degrees. The lines on the right are traced through the fibre field of this exact mesh, the one a simulation of it would use. My MSc at PUC Chile, with Francisco Sahli, is about cardiac fibre mechanics with physics-informed networks.

Two drawings of the apex of a left ventricle, its fibres whirling into a vortex, beside a diagram of their spiral paths
James Bell Pettigrew dissected the vortex at the apex in 1860 and drew its spirals by hand. Public domain.

From imagesto motion.

In Graz, from February to August 2026, I worked with Federica Caforio’s group on PINN architectures that estimate how the heart moves, in JAX. We still work together. This is the kind of data it starts from: a cine MRI, four chambers in one slice.

Cine MRI, four-chamber view, one beat. Doregan, Wikimedia Commons, CC BY-SA 4.0.

Five demos that runin your browser.

No backend, nothing pre-rendered. Each is a solver or a model running on your machine while you watch. Below, each one’s own physics, running now.

  1. PINN Playground
  2. Ask Research
  3. FNO vs. Solver
  4. Fluid Playground
  5. Optimizer Race

PINN Playground

A network learns the 1D Burgers equation with no data at all: the loss is the PDE itself, differentiated on your GPU. Behind this text, the exact solution it is trained to find, shock and all.

TensorFlow.js, WebGL, automatic differentiation

Open the demo

Ask Research

Answers over 24 passages from the scientific ML papers I read. BM25 retrieval runs in the page, as it does behind this text; bring any OpenAI-compatible key and a model answers from what it found.

BM25, retrieval-augmented generation

Open the demo

FNO vs. Solver

Same Burgers problem, two methods. The solver marches through every time step; the operator answers in one call. The demo times both on your machine instead of quoting a paper.

Neural operator, Cole-Hopf transform, finite differences

Open the demo

Fluid Playground

Jos Stam’s stable fluids in plain JavaScript. Drag across this screen to stir it: the velocity field is made divergence-free again every frame.

Navier-Stokes, canvas 2D

Open the demo
  • SGD
  • Momentum
  • RMSProp
  • Adam

Optimizer Race

SGD, momentum, RMSProp and Adam dropped on one loss surface from the same start. Momentum is the one that rolls out of the first dip.

Adam, three.js

Open the demo

About

Tomás, in a cap and round glasses

I got into machine learning through scientific computing, and most of what I’ve done since has been about making neural networks respect the physics they approximate.

My undergraduate thesis at Universidad de los Andes compressed physics-informed networks (distillation, pruning, quantization) for non-Newtonian flow. Since 2025 I’ve been doing an MSc at PUC Chile with Francisco Sahli, which took me to Federica Caforio’s group in Graz for the first half of 2026.

The rest of the time I build things to find out whether they work: the demos above, a series of language models under 16 MB, a file-transfer system that is still running at a mining company.

I’m open to ML and AI roles, remote or on-site: part-time while I finish the MSc, full-time after. Spanish is my first language and English my second; my German is just starting.

TomásSantiago, Chile

Where I’ve been.

  1. Feb to Aug 2026

    Visiting researcher

    University of Graz, Federica Caforio’s group

    PINN architectures for cardiac mechanics in JAX: differentiable PDE simulation and multi-view reconstruction scored with MSE and SSIM.

  2. Since 2025

    MSc in Engineering Sciences

    Pontificia Universidad Católica de Chile, advised by Francisco Sahli

    PINNs for cardiac fibre modelling. Grew out of the undergraduate thesis on compressing them.

  3. Since 2025

    Tiny language models

    Exploration

    Transformers under 16 MB with custom tokenizers and quantized weights, scored by bits per byte on FineWeb, trained at home on an RTX 5060.

  4. Jan to Feb 2025

    DevOps intern

    Citi, Chile Tech Center

    Kept three legacy applications running and reworked the production CI/CD pipeline so deployments took less time and fewer steps.

  5. 2024 to 2025

    Undergraduate thesis

    Universidad de los Andes, manuscript in preparation

    Distillation, pruning and quantization applied to PINN surrogates of Carbopol flow, measuring what each technique costs in accuracy.

  6. Sep 2024

    Turbo Files

    In production at a mining company

    Fault-tolerant transfer of large files in Django: files travel as fragments, so a flaky connection doesn’t kill the transfer.

  7. 2023 to 2024

    Teaching assistant, six courses

    Universidad de los Andes, computer science

  8. Dec 2023 to Feb 2024

    AI research intern

    Falabella Retail

  9. 2020 to 2025

    BSc in Computer Science engineering

    Universidad de los Andes, minor in innovation

Day to day: Python, PyTorch, JAX, CUDA; HuggingFace and TensorFlow when a project lives there. Also: JavaScript, C and C++, SQL, Django, React, Docker, AWS, Linux.