PDF version here

Education⌗

University of Trieste, Ph.D. in Applied Data Science and Artificial Intelligence⌗

  • 2024 – present
  • Trieste, Italy
  • Research project: “Converged computing: environments and technologies for hybrid HPC and Kubernetes infrastructure”

University of Trieste, Master’s Degree in Data Science and Scientific Computing⌗

  • 2022 – 2024
  • Trieste, Italy
  • Final grade: 110/110 cum laude

University of Trieste, Bachelor’s Degree in Statistics and Computer Science for Business, Finance, and Insurance⌗

  • 2019 – 2022
  • Trieste, Italy
  • Final grade: 100/110

Experience⌗

AREA Science Park, Operations Assistant during Ph.D.⌗

  • 2024 – present
  • Trieste, Italy
  • Management of the production Kubernetes cluster
  • Designed the architecture to serve a multi-user LLM on a GPU-enabled Kubernetes cluster running on-premise
  • Contributed to the maintenance of the internal distributed storage system based on Ceph
  • Assisted system administrators in on-premise cluster management

AREA Science Park, Internship⌗

  • 2023 – 2024
  • Trieste, Italy
  • Developed a solution for user authentication and authorization in a cloud environment
  • Implemented a solution based on LDAP and Kerberos to authenticate IdM users inside Kubernetes pods
  • Main technologies used: LDAP, Kerberos, Kubernetes, Vagrant, Libvirt, Docker, Podman, Ansible

Talks⌗

Seeking Cost-Optimal Infrastructure Size for Distributed File Systems: A Ceph Case Study⌗

  • March 2025
  • N. Tosato, I. Pasianotto, R. Lot, S. Cozzini
  • Presentation of an exploratory study on the impact of hardware upgrades (CPU, RAM, disk speed) on the performance of a parallel file system. CS3 2025: Cloud Storage Synchronization and Sharing – Ludwig-Maximilians University, Munich, Germany

Schools⌗

Advanced School on Applied Machine Learning⌗

  • June 2024
  • International Centre for Theoretical Physics (ICTP), Trieste, Italy
  • Presented a poster titled “Gaussian processes for time-series data analysis: case study for a large dataset”

Skills⌗

  • Programming Languages: Proficient in C, Python, and Bash, with strong experience in scientific computing and systems programming. Working knowledge of C++, R, and Java. Basic familiarity with Rust, Julia, and front-end development (HTML, CSS, JavaScript).
  • Parallel & Distributed Computing: Experienced in high-performance computing (HPC) environments, including parallel programming with MPI, OpenMP, OpenACC, and CUDA. Skilled in building distributed workflows using Python tools such as Dask and PyTorch, and familiar with scheduling and resource management systems like SLURM.
  • Cloud & Infrastructure: Experienced in designing, deploying, and maintaining Kubernetes clusters in both bare-metal and virtualized environments. Familiar with distributed storage solutions (e.g., Ceph) and identity management systems. Knowledgeable in disaster recovery, backup planning, and network configuration in virtualized infrastructures.
  • Containerization & Virtualization: Skilled in container-based development and deployment workflows using Docker and Podman. Experienced with Vagrant and virtualization platforms (Libvirt, Proxmox, and QEMU) for creating reproducible environments. Proficient in building infrastructure automation pipelines that integrate containers, virtual machines, and orchestration layers.
  • DevOps & Automation: Strong background in Infrastructure as Code (IaC) and configuration management with Ansible and OpenTofu/Terraform. Highly familiar with Helm for Kubernetes deployments and GitOps practices.
  • OS & Environment: Proficient in Linux system administration, shell scripting, and command-line tools. Experienced with Git-based workflows and remote system management. Skilled in interacting with HPC schedulers and debugging performance issues in parallel environments.
  • Identity & Access Management: Experienced in deploying and customizing IAM platforms such as Authentik, including custom enrollment flows and secure provisioning of SSH keys. Working knowledge of FreeIPA and its integration with containerized and cloud environments.
  • Monitoring, Logging & Tooling: Familiar with Unix/Linux monitoring and troubleshooting tools (htop, iftop, journalctl, etc.), log aggregation, and basic observability practices. Comfortable with advanced text editors (Vim, Emacs) and terminal multiplexers (Tmux).
  • Infrastructure Orchestration & Testing: Experience in building reproducible testbeds and simulation environments using Vagrant, Ansible, and Kubernetes. Skilled in provisioning multi-VM environments for complex systems (HPC clusters, Ceph storage, FreeIPA) and integrating them into automated CI pipelines.

Personal Projects⌗

STENCIL⌗

  • 2023 – present
  • Modular approach for both deployment and provisioning stages
  • Integrated a Kubernetes cluster, an Identity Management System, a distributed filesystem, and SLURM as a job scheduler
  • Completely declarative: built on OpenTofu and Ansible

dask-bench⌗

  • 2023 – 2024
  • Compatible with SLURM and Kubernetes scheduling systems
  • Used to evaluate Kubernetes overhead on identical hardware
  • Based on the concept of Weak Scaling, executing various workloads with arrays and dataframes

Federated Learning⌗

  • 2024 – 2024
  • Scalable simulation both vertically (per-node resources) and horizontally (number of nodes)
  • Uses an adapted AlexNet architecture for image classification

Contributions⌗

freeipa-scim⌗

  • 2024 – 2025
  • Participated in the development of the code
  • Managed the production deployment on Kubernetes clusters

slurm-helm⌗

  • 2023 – 2024
  • Contributed to templating the chart
  • Integrated an IPA client-like configuration based on LDAP+Kerberos to query a FreeIPA server for users’ UID and GID

Certifications⌗

NVIDIA Deep Learning Institute⌗

  • October 2024

Languages⌗

  • English: Proficient in both written and spoken English
  • Italian: Native speaker

Teaching⌗

  • Foundations of HPC: Assistant lecturer for the course taught at the Master’s degree in Data Science and Scientific Computing at the University of Trieste
  • Scientific Programming Method: 18-hour module at the Master in Data Management and Curation (MDMC) organized by SISSA and AREA Science Park
  • Cloud Computing, 2024: Delivered a 2-hour lecture in the Advanced Cloud Computing course on CNI plugins and multi-node communication in Kubernetes clusters.

Volunteering⌗

  • AI2S: Member of the Artificial Intelligence Student Society (AI2S), a student association active in the Trieste area.