Personal Profile

My main interest is Machine Learning and its application to computer vision, robotics and 3D understanding. I am always learning about the latest technologies (NeRF, diffusion models, etc.), while maintaining a strong grasp of foundational concepts. My skills combine a solid mathematical background with practical implementations by programming. With these, I aim to contribute to discovering new ways in which machine learning can help improve computer vision, AR, graphics, and autonomous systems.

Education

• MSc in Robotics, Graphics and Computer Vision
  Universidad de Zaragoza, Zaragoza (Spain)
  09/2024 – Present
  Score (1st semester): 9.22 / 10

• BSc in Computational Mathematics
  Universitat Jaume I, Castellón de la Plana (Spain)
  09/2019 – 07/2023
  Score: 9.26 / 10
  Thesis: Geometric foundations for Geometry Processing of Neural Implicit Representations of Signed Distance Functions

Experience

• AI/CV Researcher
  Ropert group, Universidad de Zaragoza (Spain)
  09/2024 – Present

  • Dense Visual SLAM for in‑body robotics.
  • Depth estimation and geometric SLAM combined with learned methods.

• AI/CV Engineer
  Machine Learning Circle, Madrid (Spain)
  03/2024 – 08/2024

  • Learned semantic matching.
  • Deep generative models and representation alignment.

• AI/CV Engineer
  Hovering Solutions, Madrid (Spain)
  09/2023 – 02/2024

  • Developed algorithms and software (ROS, C++, Python) for autonomous underground drones.
  • Applied deep learning for perception and reconstruction (NeRF, Deep SLAM, SFM, etc.).

• Study and Research Program
  eVIS, Universitat Jaume I (Spain)
  09/2020 – 06/2023

  • Research and training on the latest Deep Learning techniques for Computer Vision.
  • Participated in reading groups, scientific writing, and project contributions.

• Introduction to Research Grant
  INIT, Universitat Jaume I (Spain)
  09/2021 – 12/2021

  • Modeled the salience of video frames using 3D‑CNN.

• Research Assistant
  eVIS, Universitat Jaume I (Spain)
  12/2019 – 06/2020

  • Collaborated on ML projects in Computer Vision and learned research fundamentals.

Internships

• HPC Intern
  Karlsruhe Institute of Technology (Germany)
  07/2023 – 08/2023

  • Optimized the ELL kernel of the Ginkgo library for matrix–vector multiplication.

• Independent Consultant
  Common Sense Machines (Remote)
  11/2022 – 02/2023

  • Integrated ML models into user‑facing applications.

• VR Intern
  University of Eastern Finland (Finland)
  07/2022 – 09/2022

  • 3D capture (NeRF) and holographic display.
  • Brain–Computer Interfaces in VR.

• Robotics Apprenticeship
  Ingeniarius (Portugal)
  07/2021 – 09/2021

  • Integrated four RGB‑D cameras to perform SLAM in simulated forest environments.

Awards & Honors

• VII Premios Capitanía General de Valencia
  Best academic record in Engineering/Architecture (Valencian Community).

• Extraordinary End‑of‑Degree Award
  Best record, 2019–2023 BSc Computational Mathematics.

• Academic Excellence Ernest Breva
  Best record, academic year in BSc Computational Mathematics.

Publications

• Characterizing Players of a Cube Puzzle Game with a Two‑level Bag of Words
  UMAP ’21: Adjunct Proceedings of the 29th ACM Conference · June 22, 2021

Certified Courses

• Natural Language Processing with Classification and Vector Spaces
  Deeplearning.ai (Coursera) · 10/2020 – 12/2020
  Credential: [link]

• Deep Learning Specialization
  Deeplearning.ai (Coursera) · 07/2020 – 09/2020
  Credential: [link]

Audited Courses

• Build Basic Generative Adversarial Networks (GANs)
  Deeplearning.ai (Coursera) · 07/2022 – 09/2022

• NYU Deep Learning
  New York University · 02/2022 – 07/2022 (Online)

• Deep Learning For Coders
  Fastai · 01/2021 – 06/2021 (Online)

Projects

• Personal Blog
  A blog covering topics and experiments from my research and projects. [Link]

• Efficient Deep Learning Book
  Contributed to code labs, porting TensorFlow implementations to PyTorch. [Link]

Additional Skills & Languages

• Programming Languages: Python, C/C++, Java, Matlab, etc.
• DL Frameworks: PyTorch, Fastai, Hugging Face ecosystem, etc.
• DL Theory: NeRF, Transformers, VAEs, GNNs, diffusion, etc.
• Mathematics: Algorithms, geometry.
• Computer Science: OpenCL, OpenMP, MPI.
• Languages: Spanish (Native), English (C1 Advanced)

Undergraduate Final Thesis (TFG)

Neural fields are neural networks that take spatiotemporal coordinates as input and output values for those points. One of the most well-known applications is Neural Radiance Fields (NeRFs); however, they span robotics, graphics, and shape representation. This TFG presents fundamental concepts from differential geometry (differentiability, curvature) to process shapes represented as signed distance functions (SDFs) approximated by neural networks. It covers background needed for shape smoothing and sharpening directly on the implicit representation, as proposed in “Geometry Processing with Neural Fields” (NeurIPS 2021). We study both geometry and neural basics, including mesh‑to‑implicit conversion.

Thesis Repository • TFG PDF