CV

Senior Staff Scientist at Lawrence Livermore National Laboratory working at the intersection of AI for science, machine learning, and scientific computing. My work combines research leadership and hands-on development across antibody design, interpretable modeling, optimization, and high-performance simulation, with publications in venues including Nature, Science Advances, NeurIPS, ICML, and AAAI.

• Resume
• Academic CV

Education

• Ph.D. in Applied Mathematics, Oct. 2012 - Mar. 2016,
  Université Pierre et Marie Curie and Inria, Paris, France 🇫🇷.
  Thesis defended on 29th March 2016 (mention très honorable).
  You can get the manuscript here.

• Master program in Scientific Computing (Erasmus Exchange Program), 2011 - 2012,
  Utrecht University, Utrecht, The Netherlands 🇳🇱.

• B.S. and M.S in Mathematical Sciences, 2007 - 2012,
  University of the Basque Country, Bilbao, Spain 🇪🇸.
  Premio extraordinario de carrera

Work experience

• Senior Staff Scientist, Jul. 2020 - Present
  Computational Engineering, Lawrence Livermore National Laboratory, Livermore, US 🇺🇸.

• Postdoctoral Fellow, Jul. 2018 - Jul. 2020
  Biochemical and Biophysical Systems Group, Lawrence Livermore National Laboratory, Livermore, US 🇺🇸.
  Topic: Machine Learning for Heart Electrophysiology

• Postdoctoral Fellow, Apr. 2016 - Apr. 2018
  MOX - Dipartimento di Matematica, Politecnico di Milano, Milano, Italy 🇮🇹.
  Topic: Computational Heart Electrophysiology

• Research Internship, Jun. 2011- Jul. 2011
  Basque Center for Applied Mathematics, Bilbao, Spain 🇪🇸.
  Topic: Burgers equation Get the report here.

Leadership & Program Ownership

• Principal Investigator, LDRD Exploratory Research ($2M over 3 years), Oct. 2023 - Oct. 2026
  Lawrence Livermore National Laboratory, Livermore, US 🇺🇸.
  Generative Transformers for Optimization, a Laboratory Directed Research and Development (LDRD) Exploratory Research project.

• Team Lead, Deep Symbolic Optimization thrust, Apr. 2023 - Sep. 2023
  Generative Unconstrained Intelligent Drug Engineering (GUIDE), Lawrence Livermore National Laboratory.
  Led the Deep Symbolic Optimization thrust, coordinating a team of 9 researchers.

• Lead Mentor, Data Science Challenge, Jan. 2023 - Jun. 2023
  Data Science Challenge, Lawrence Livermore National Laboratory.
  Lead organizer and mentor for the laboratory-wide program.

• Program Lead, ML Training Pilot Program, Apr. 2022 - Sep. 2022
  Data Science Institute (DSI) and Center for Applied Scientific Computing (CASC), Lawrence Livermore National Laboratory.
  Led development of a deep reinforcement learning curriculum for both divisions.

Academic Service

• Reviewer

- International Journal for Numerical Methods in Biomedical Engineering
- Artificial Intelligence Review
- Neural Computing and Applications
- Neural Information Processing Systems
- International Conference on Learning Representations
- International Conference on Autonomous Agents and Multiagent Systems
- Machine Learning

• Editorial Work

- Guest Associate Editor in Coronary Artery Disease in Frontiers in Cardiovascular Medicine
- Editorial board member of the American Journal of Computer Science and Technology

Skills

LLM & agentic systems — Claude Code, Anthropic API, OpenAI API; structured outputs under JSON schema, LLM-as-prior and LLM-as-tool patterns, autoresearch loops, prompt-design ablation, few-shot calibration; hybrid pipelines that pair an LLM with a deterministic backend (solver, fixed evaluation protocol) for auditable, overridable results.

Machine learning & deep learning — PyTorch, Hugging Face Transformers, TensorFlow, Keras, scikit-learn; reinforcement learning (PPO with KL regularization, REINFORCE, offline RL via Direct Reward Optimization, risk-seeking policy gradients); sequence and protein language models (IgLM, ProtBert, AntiFold/ESM-IF); CNNs for signal-to-signal reconstruction.

Optimization & interpretable modeling — integer linear programming, constrained multi-objective optimization (Pareto fronts, hypervolume, diversity constraints), genetic programming, symbolic regression, decision-tree and closed-form control policies.

High-performance & distributed computing — C/C++ with MPI and OpenMP, CUDA, PETSc, Trilinos, MFEM; GPU training and large-scale simulation campaigns on LLNL supercomputers (Lassen); Spack-based builds.

Engineering & tooling — Python packaging and release to PyPI, GitHub Actions CI, pytest, black/flake8, Git/GitHub, configuration-driven experiment pipelines, HDF5/NumPy/Pandas data pipelines.

Programming languages — Python, C/C++, Wolfram Language, MATLAB, LaTeX.

Open-source — ProtLib-Designer, ProteinTuneRL, DSO, cardiac_ml, Cardioid; see Projects for details.

Also — FreeFem++, Gmsh, VMTK, ParaView, EnSight, FELiScE, LifeV, Mathematica (Wolfram Demonstrations), SVN. Personal PyTorch examples are here.

Languages

• English 🇺🇸 : Proficient.
  
• Spanish 🇪🇸 : Mother tongue.
  
• French 🇫🇷 : Fluent.
  
• Italian 🇮🇹 : Fluent.
  
• Basque 󠁥: Basic.