CV

Experience

---

• Responsible for developing Grazper’s model training pipeline, training and optimizing pose estimation and box detection models central to our human pose recognition system.

• Developed and maintained a 3D human-pose annotation web application, now actively used by annotators to label our in-house dataset.

• Built an auto-annotation system using state-of-the-art models and postprocessing to accelerate the annotation process.

• Automated key steps in the recording pipeline (actor registration, video export, and auto-annotation) through custom scripts and applications.

• Led the migration to GitHub, establishing reproducible test environments for Grazper’s CI/CD pipelines on self-hosted GitHub runners. Deployed a self-hosted package registry for managing Python and npm packages, and Docker images, improving significantly the development process of the entire company. Check out this post for more details.

• Researched and developed a method to enhance 3D human pose estimation using an IoT sole pressure system to improve accuracy with fewer cameras. Designed a supervised model that predicts sole pressure, enabling real-world applications without the IoT device.

---

• I was responsible for data processing, analysis and visualization of the HR department of Novo’s main production site.

---

• Assisting in the course 02450 - Intro to Machine Learning and Data Mining. I taught a group of 40+ students during weekly labs.

Technical skills

Languages

Machine learning

Numerical

Networking

DevOps

Data viz

Frontend

---

Projects

Here are some of the projects I’ve done in the past or I’m currently doing now:

• ScaleGuru
  Written entirely in TypeScript. A tool designed for musicians to refine their mastery of scales and keys. The tool asks for a given scale in a specific key, hiding the scale so that users must play from memory. It allows for playback to check if the scale was played correctly (ear training) or displays the scale for users who are still learning it.
• Sudoku Solver
  Toy project where I build a web-app solution that lets you upload a picture of a sudoku and solves it. Currently in development.
• Bayesian Methods for Electroencephalogram (EEG) Decoding
  Implementing and comparing the performance of different Bayesian Neural Networks (Ensembles/SWA/SWAG/MultiSWAG) with state-of-the-art deep learning techniques in the task of classifying EEG readings while the test subjects imagines performing a task.
• Time Series Anomaly Detection with Variational AutoEncoder and GRU
  Project for DTU’s course Advanced Machine Learning researching the potential of using Variational Autoencoders in combination with RNNs for anomaly detection on time-series data. Download the paper here.

---

Education

• MSc in Mathematical Modelling and Computation at DTU: 09/2020 - 02/2023
  Worked on courses and group projects involving different topics in machine learning, computer science and applied mathematics: deep learning, bayesian machine learning, MLOps, algorithms and data structures, high performance computing, dynamical systems theory, stochastic processes, optimization…

• BSc + MSc in General Engineering at UPV: 09/2015 - 07/2020
  Studied a broad variety of courses in general engineering competences, including maths, physics, statistics, thermodynamics, materials, mechanics, electronics, automatics and electrical engineering, among others. Specialized in Electrical Engineering thanks to the research internship I did in the department of Electrical Engineering. Additionally, I studied Jazz at the same time at Sedajazz music academy in Valencia.