Experience

Fall 2018 - present

Cambridge, MA

MIT - Graduate Research Assistant

  • Conducting fully-funded research on Reinforcement Learning and Mathematical Programming algorithms for Dynamic Resource Management in satellite mega-constellations
  • Initiated and now leading a sponsored 2-year-long research project on Reinforcement Learning for drug discovery and molecular optimization
  • Mentored 10 undergraduate students and directly supervised 4 undergraduate Thesis
  • Participated in 9 conferences and workshops
  • Every semester I take on a side project connected with Reinforcement Learning or other state-of-the-art Machine Learning areas (e.g., Graph Neural Networks, Meta Learning)

Fall 2020 - present

Cambridge, MA

MIT - Graduate Lead

  • Leading a team of 4 graduate students working on the design of the next generation of Resource Allocation and Revenue Management systems for highly-flexible mega-constellations
  • This project is sponsored by SES: our team reports monthly to SES engineers and holds a semiannual review with the CTO and other senior managers
  • Every year I co-lead the organization of a knowledge transfer workshop with engineers at SES HQ in Luxembourg

Fall 2021 - Spring 2022

Cambridge, MA

Google Brain - Student Researcher

  • Applied MetaPG, the framework developed during my internship, to a use case on evolving RL algorithms that optimize and trade high returns, generalizability, and stability
  • Our method was able to find RL algorithms that improve upon SAC's performance and generalizability by 3% and 17%, respectively, and reduce instability up to 65%
  • Actively communicated with research scientists among the Reinforcement Learning, AutoML, and Robotics teams at Google Brain
  • Routinely presented my work to larger audiences in seminars or group meetings across Google Brain

Summer 2021

Remote

Google Brain - Research Intern

  • Designed, implemented, and tested MetaPG: a multiobjective Meta Evolution framework to optimize multiple Reinforcement Learning goals simultaneously and gain insights on underlying tradeoffs
  • MetaPG provides a proof-of-concept for bridging the gap between the design of RL algorithms and the needs of RL practitioners

Summer 2020

Remote

Novartis AI Innovation Lab - Machine Learning Engineer Intern

  • Developed Deep Reinforcement Learning models for molecular design and molecular property optimization, achieving better performance than state-of-the-art models on a subset of tests from the Guacamol benchmark suite
  • The project was framed inside a collaboration between Novartis and Microsoft Research, I routinely presented my work to researchers in both companies

Fall 2017 - Summer 2018

Barcelona, Spain

ARCVI - Data Scientist

  • Developed injury risk prediction models that outperformed previous methods' accuracy by 20% (impact of 90-170k€)
  • Defined a new disposal architecture for 1,500 vending machines by means of Mathematical Programming, with an estimated impact of 380k€
  • Developed consumption likelihood models for retail vendors and designed commercial strategies using behavioral economics principles
  • Co-authored the business report Adoption and Impact of Big Data and Advanced Analytics in Spain [Spanish version]

Fall 2016

Barcelona, Spain

Barcelona Supercomputing Center - Undergraduate Research Assistant

  • Adapted different Machine Learning models for large-scale multiprocessing architectures
  • After testing on the MareNostrum 4 supercomputer, our algorithms resulted in a 10x speed increase for high-dimensional clustering tasks

Skills

  • Python: Expert. Frequent use of PyTorch, JAX, Tensorflow, Numpy, scikit-learn, Pandas, and Gurobi

  • Julia: Intermediate. Mathematical Programming toolbox

  • Other technologies: MATLAB, R, LaTeX, Git

Participation in conferences and workshops

2022 - Reviewer - Reinforcement Learning for Real Life Workshop at NeurIPS 2022

2022 - Reviewer - IEEE Transactions on Wireless Communications

2022 - Presenter - International Astronautical Congress 2022

2022 - Presenter - Generalizable Policy Learning for the Physical World Workshop at ICLR 2022

2022 - Presenter - AI to Accelerate Science and Engineering Workshop at AAAI 2022

2021 - Presenter - Reinforcement Learning for Real Life Workshop at ICML 2021

2021 - Reviewer - Reinforcement Learning for Real Life Workshop at ICML 2021

2021 - Presenter - IEEE Aerospace Conference 2021

2020 - Presenter - IEEE Aerospace Conference 2020

2019 - Presenter - Reinforcement Learning for Real Life Workshop at ICML 2019

2019 - Presenter - IEEE Cognitive Communications for Aerospace Applications Workshop