tomás.erdmannsdörffer
open to roles
graz, austria · santiago, chile msc engineering @ puc chile visiting researcher @ uni graz

Tomás Erdmannsdörffer
builds ML systems where
physics meets code.

Machine learning engineer with a foundation in scientific computing and deep learning. I work the full stack — training and compressing models, building LLM pipelines, shipping backends to production. Currently researching cardiac fiber modeling with Physics-Informed Neural Networks at the University of Graz.

4yrs
building software
3live
in-browser ML demos
3internships
citi · falabella · graz
6courses
taught as TA
·

Currently

may 2026

Researching cardiac fiber mechanics with PINNs.

I'm three months into a visiting research stay at the University of Graz, working with Dr. Federica Caforio on physics-informed neural networks for myocardial tissue modeling. Most of my time goes into my MSc thesis project: applying PINNs to cardiac modeling.

On the side, I'm building browser-side ML demos — the two on this page — and competing in OpenAI's Parameter Golf, a sub-16MB language model competition.

  • research WarpPINN-Fiber adaption — PINNs for cardiac modeling.
  • writing Compression thesis manuscript — knowledge distillation + pruning + quantization on PINNs.
  • competition OpenAI Parameter Golf — sub-16MB language model on FineWeb bpb, RTX 5060 Blackwell.
  • building Browser ML demos — PINN playground & RAG over scientific papers (both live on this page).
01

Live Demos

both run in your browser · no install
02

My Journey

2020 → today
feb 2026 — present · graz, AT

Visiting Researcher research

Karl-Franzens-Universität Graz · with Dr. Federica Caforio

Working on PINNs for cardiac modeling in JAX.

JAXPINNCardiac Modeling
aug 2025 — present · santiago, CL

MSc in Engineering Sciences education

Pontificia Universidad Católica de Chile · Mechanical Engineering · advised by Prof. Francisco Sahli

Researching PINNs for cardiac fiber modeling applied to PDEs — the foundation of my work in Graz. The MSc deepens what started as a thesis on compressing PINNs.

JAXPyTorchPDEsBiomechanics
jan — feb 2025 · santiago, CL

DevOps Intern internship

Citi · Chile Tech Center

Maintained and optimized 3 legacy applications, improved the production CI/CD pipeline to reduce operational complexity and deployment time, and collaborated on code migration via Bitbucket.

3legacy apps optimized deployment time reduced
JenkinsBitbucketCI/CDDocker
2024 — 2025 · santiago, CL

Undergrad Thesis — PINN Compression research

Universidad de los Andes · manuscript in preparation

Applied knowledge distillation, pruning, and quantization to PINN surrogates for non-Newtonian (Carbopol) fluid simulation. Built the baseline PINN end-to-end, then quantified precision vs. efficiency trade-offs across techniques.

3compression techniques studied PyTorchbaseline + students
PyTorchPINNQATDistillationCFD
jun 2023 — dec 2024 · santiago, CL

Teaching Assistant (×6 courses) teaching

Universidad de los Andes · CS Department

Supported ~30 students per semester across Operating Systems, Low-Level Programming (C/C++), Mobile Apps, Web Technologies, Automata & Computability, and Programming Fundamentals.

6distinct courses ~30students per semester
C/C++PythonLinuxWeb
dec 2023 — feb 2024 · santiago, CL

AI Research Intern internship

Falabella Retail

Researched generative AI tools for retail. Built a functional prototype for automated product descriptions, transforming a manual process into an automated flow. Delivered a technical proposal that continued in development post-internship.

LLMpipeline + prompt engineering proposal kept in dev post-intern
LLMPythonPrompt Eng.
mar 2020 — oct 2025 · santiago, CL

BSc Civil Engineering in Computer Science education

Universidad de los Andes · Minor in Innovation

Coursework: Low-Level Programming, AI, LLM, Computer Vision, Algorithms & Competitive Programming, Databases, Web Technologies, Data Structures.

PythonC/C++PyTorchReactSQL
03

Research & Software

beyond the demos

MSc Thesis MSc thesis

2025 — present

Working on PINNs for cardiac modeling in JAX.

JAXPINNCardiac Modeling

Parameter Golf competition

2025 — present

OpenAI public competition: build a language model under 16MB, scored by bits-per-byte on FineWeb. Designing custom tokenizers and quantized Transformer architectures.

  • Targeting RTX 5060 Blackwell (sm_120, PyTorch cu128 nightly).
  • Background in PINN compression directly applicable.
PyTorchCUDAQuantizationTokenizers

Turbo Files production

sep 2024

Fault-tolerant data transfer system shipped to a mining company in production. Fragments large files for resilience over intermittent connectivity.

  • Google Drive + AWS S3 integration with variable file sizes.
  • Built end-to-end in Django.
DjangoAWS S3Drive API

Toma de Ramos leadership

sep 2023

Led a team of 7 building a web-based academic scheduler. Used by the entire Universidad de los Andes for one full year.

  • Credit validation + schedule conflict detection.
  • Django backend, React frontend.
DjangoReactTeam of 7
04

Stack

ML / AI [core]
  • PyTorch
  • JAX
  • TensorFlow · Keras
  • HuggingFace
  • CUDA
  • PINNs · diff. sim
  • RAG · LLM agents
Languages [code]
  • Python
  • JavaScript
  • C / C++
  • C#
  • SQL
  • LaTeX
Backend & Web [apps]
  • Django
  • Node.js
  • React
  • Ruby on Rails
  • REST APIs
DevOps & Cloud [ops]
  • Docker · Git
  • AWS (S3, Lambda)
  • Jenkins · Bitbucket
  • CI/CD
  • Linux · WSL2
spoken Spanish native
English C2 (IELTS)
German A1
05

Contact

Let's build something that actually runs.

Open to ML/AI engineer roles — remote, hybrid, or on-site globally. Available part-time now; full-time after MSc completion.

location Graz, Austria · Santiago, Chile