Mikel Landajuela

Mikel Landajuela

Senior Staff Scientist in AI for Science, Machine Learning, and Scientific Computing

Mikel Landajuela

I lead AI-for-science and scientific-computing teams at Lawrence Livermore National Laboratory in the Computational Engineering Directorate, building AI and scientific-computing capabilities for national mission-critical problems — accelerating drug development, enabling rapid response to emerging biothreats, advancing non-invasive medical diagnostics, and powering high-performance simulation. My work spans deep learning, reinforcement learning, optimization, interpretable models, and agentic AI pipelines paired with deterministic backbones for auditable scientific applications, with publications in Nature, NeurIPS, ICML, and AAAI. I earned my Ph.D. from Université Pierre et Marie Curie and Inria in Paris, and received the SMAI-GAMNI award 2017 from the French Society of Industrial and Applied Mathematics.

Expertise: machine learning · reinforcement learning · optimization · interpretable AI · scientific computing · mathematical modeling · agentic AI

Projects & Focus Areas

  • AI for National Mission-Critical Science : Building capabilities-based AI systems on GPU/HPC infrastructure to accelerate scientific discovery in high-stakes domains — from therapeutic design and biodefense preparedness to medical diagnostics and engineering simulation. Recent work includes deep-learning pipelines for drug development and agentic LLM workflows that compress the research loop on mission-relevant problems.

  • Interpretable & Responsible AI : Crafting symbolic-regression methods and decision-tree controllers to ensure transparent, auditable ML workflows suitable for regulated environments.

  • High-Performance Scientific Computing : Designing scalable PDE solvers for fluid-structure interaction and cardiovascular mechanics, optimizing C++/Python code across on-prem and cloud HPC environments.

I welcome research collaborations and industry partnerships. ✉️ landajuelala1 at llnl dot gov · 🔗 Google Scholar

Download Resume LinkedIn ROC/PR Playground

Selected Highlights

  • 2025-09-23: Keynote speaker at AI for SCIENCE 2025, Ljubljana, Slovenia.
  • 2025-03-28: Preemptive optimization of a clinical antibody for broad neutralization of SARS-CoV-2 variants and robustness against viral escape published in Science Advances.
  • 2024-05-08: Computationally restoring the potency of a clinical antibody against Omicron published in Nature.
  • 2022-09-14: A Unified Framework for Deep Symbolic Regression accepted at NeurIPS 2022. (openreview)

Selected Publications

  • Preemptive optimization of a clinical antibody for broad neutralization of SARS-CoV-2 variants and robustness against viral escape. Science Advances, 2025. Journal
  • Computationally restoring the potency of a clinical antibody against Omicron. Nature, 2024. Journal
  • DisCo-DSO: Coupling Discrete and Continuous Optimization for Efficient Generative Design in Hybrid Spaces. AAAI, 2025. Paper
  • A Unified Framework for Deep Symbolic Regression. NeurIPS, 2022. OpenReview

More publications are available on the Publications page.