Federico Padua

- Development and deployment of multiple APIs, backend UIs. Performed code reviews, made technical choices when needed, mentored a junior colleague. - Development of a core backoffice banking system based on event-driven design and REST APIs. Performed design, development, deployment, code reviews and started developers' documentation. - Built dashboards and the data engineering part to feed them. - Internal APIs development, developers' documentation, code reviews, video tutorials, POCs development.

- I worked within the Azure Storage Research Lab on Project Silica, a storage system to ''store data in quartz glass by using femtosecond lasers'' (https://www.microsoft.com/en-us/research/project/project-silica). I contributed software in C#, Python and Powershell for data analysis and for modelling a storage system. - The data analysis helped to drive and understand the simulation and the usage of a large-scale storage system running in production.

- Research and development in parallel file I/O, trace and characterization of storage systems and High Performance Computing (HPC) applications. - Implemented binary parallel file I/O within the production-grade open source parallel scientific software ESPResSo++, using MPI and HDF5 which substantially improved input-output. Contributed Python software that was added to Spack. - Design, setup, implementation and analysis of software experiments on small to large-scale computer clusters.

Original developer for the prototype of an HPC I/O tracing and characterization system. I defined research questions that would drive the design of the system. The work was presented in a poster which was awarded best poster award.

I analyzed HPC cluster jobs' logs and identified trends and patterns, like weekday/weekend cycles, day/night cycle, major data movement contributors in multiple HPC clusters and job sizes trends.

HPC I/O research, parallel file systems and monitoring tools used in systems research.