About me

Hi there! I am a senior research scientist at Microsoft Research MSR in Cambridge, UK. My primary goal at the moment is to contribute with the necessary machine learning approaches to personalise and enhance gene-based immunotherapies to fight back cancer and other diseases.

Before joining MSR, I was part a postdoctoral fellow at Harvard University, advised by Finale Doshi-Velez, working on interpretable machine learning, probabilistic modeling, and healthcare applications. I primarily focused on personalising antidepressant prescriptions and designing meaningful priors for deep Bayesian models.

As my background goes, I am originally a Telecommunication Engineer, and jumped into probabilistic machine learning working in industry for two years on recommendation systems at Sony Corporation R&D, first in Germany and then Japan. I got my PhD "Bayesian non-parametric models for data exploration" from University Carlos III in Spain, under the supervision of Fernando Perez-cruz. On the personal side, I love Japanese culture, sports of any kind (e.g., ice-skating, yoga, hiking), and taking care of my dwarf rabbit.

See my CV for further information about me.


  • 2021-06: Check out our HCI works on Designing AI for trust and collaboration in Time-Constrained Medical Decisions and "How ML recommendations influence clinican treatment selections

  • 2021-03: We presented our work Preferential MoE: Interpretable Models that Rely on Human Expertise as much as possibleat AMIA 2021 Virtual Informatics Summit

  • 2020-12: I am co-organizing the NeurIPS workshop ``I can't believe it is not better'' ICBINB@NeurIPS 2020. Come check it out!

  • 2020-11: Very excited to join Microsoft Research as a Senior Research Scientist in Cambridge, UK!

  • 2020-05: Our paper on generating interpretable predictions for antidepressant treatment stability just got published to JAMA Network Open!

  • 2020-04: How to incorporate functional prior knowledge in Bayesian RBF NNs? Our work just got accepted to UAI Conference! Check it out here: Poisson Process Radial Basis Function Networks.

  • 2020-02: Who gets an initial antidepressant prescription and then never follows up? Check out our latest publication in Nature Translational Psychiatry.

  • 2019-12: We will present a poster at the AABI Workshop on "Challenges in Computing and Optimizing Upper Bounds of Marginal Likelihood based on Chi-Square Divergences".

  • 2019-11: I am happy to announce that our work "General Latent Feature Models for Heterogeneous Datasets" has been accepted for publication at the Journal of Machine Learning Research!

  • 2019-06: We will be teaching a new master course "Introduction to Machine Learning and Statistics`` and Workshop on Data Science at Kigali, Rwanda. Thanks to the African Center of Excelence in Data Science (ACE-DS)'' for the opportunity!

  • 2019-05: Check out our recent work on Output-Constrained Bayesian Neural Networks, to be presented at ICML2019 Workshop on Generalization.

  • 2019-03: I will be talking as a panelist member at the event ``Data Science Everywhere'' organized by Harvard Big Data Club.

  • 2019-03: I will be a mentor at the ``Women in Data Science Cambridge'' organized by the Institute of Applied Sciences at Harvard and Microsoft Research.

  • 2019-02: We have been awarded a HDSI competitive research fund for our project ``Personalizing mental health care: Bringing machine learning support into the clinic through user-centered design''.

  • 2019-01: Our new work on Hierarchical Stick-breaking Feature Paintbox was presented at the NeurIPS'18 workshop on Bayesian Nonparametrics as a spotlight talk.

  • 2018-12: Check-out our new work on projected Bayesian neural networks. A shorter version appeared at the NeurIPS'18 workshop on Bayesian deep learning.

  • 2018-11: I recently gave a talk "Towards better uncertainty in Bayesian Neural Networks" at IBM Research in Cambridge, and University Carlos III in Madrid.