Skip to content

Curriculum vitae

Lucas de Sousa Rosa

Doctorate student in the Computer Science program working with the Software Systems Research Group at the Institute of Mathematics, Statistics and Computer Science (IME) of the University of São Paulo (USP). Graduated in Molecular Sciences in the same institution. Active in scientific research since 2020, supported by multiple prestigious Brazilian scholarships including FAPESP Technical Training (TT-1), Scientific Initiation (IC), Research Internship Abroad (BEPE), and Doctoral Fellowships (PROEX CAPES/DD FAPESP).

Figure 1. Six scholarships, six papers, two courses and two honors on one time scale. Red is under way today; dashes are still ahead.
201920202021202220232024202520262027studyDoctorate, Computer ScienceBSc., Molecular SciencesgrantsBEPE-DDFAPESP DDCAPES PROEXBEPE-ICFAPESP ICFAPESP TT-1workGrenobleteachingIntro to ComputingParallel ProgrammingpapersThe Environmental Impacts of High-Performance Computing: A Systematic Mapping StudyEnergy-Aware Scheduling for Serverless Scientific Workflows: A Machine Learning ApproachAn Experimental Analysis of Regression-Obtained HPC Scheduling HeuristicsOn limits of Machine Learning techniques in the learning of scheduling policiesExploring Simplicity and Efficiency: Regression-based Scheduling Heuristics in HPCIn search of efficient scheduling heuristics from simulations and Machine LearninghonorsCTIC top 10CTIC top 10WIC mentionWIC mentiontoday · Nov 2026

Education

  1. 2023 – present

    Doctorate in Computer Science

    Universidade de São Paulo

    São Paulo, SP

  2. 2019 – 2023

    BSc. in Molecular Sciences, emphasis on Computer Science

    Universidade de São Paulo

    São Paulo, SP

Professional experience

  1. Feb – May 2026

    Ingénieur d’Études

    Université Grenoble Alpes

    Developed a simulation environment and a SimGrid plugin to model water consumption and carbon emissions of high-performance computing platforms. This environment was used to evaluate environmental-aware scheduling heuristics aiming to balance environmental impact with system performance.

Publications

  1. 2026

    The Environmental Impacts of High-Performance Computing: A Systematic Mapping Study

    Rosa, L. de S., Lima, V. P., Carastan-Santos, D., Da, A. A., Amaris, M., de Camargo, R. Y., & Goldman, A.

    HAL.

    hal-05601113

  2. 2024

    Energy-Aware Scheduling for Serverless Scientific Workflows: A Machine Learning Approach

    Rosa, L., & Goldman, A.

    Proceedings of the 15th Regional School of High-Performance Computing of São Paulo. pp. 89–92. Porto Alegre: SBC.

    10.5753/eradsp.2024.239934

  3. 2023

    An Experimental Analysis of Regression-Obtained HPC Scheduling Heuristics

    Rosa, L., Carastan-Santos, D., & Goldman, A.

    Job Scheduling Strategies for Parallel Processing (JSSPP 2023). Klusáček, D., Corbalán, J., Rodrigo, G.P. (eds). Lecture Notes in Computer Science, vol 14283. Springer, Cham.

    10.1007/978-3-031-43943-8_6

  4. On limits of Machine Learning techniques in the learning of scheduling policies

    de Sousa Rosa, L., Carastan-Santos, D., Goldman, A., & Trystram, D.

    Electronic Journal of Undergraduate Research on Computing. 21(2), 61–70.

    10.5753/reic.2023.3419

    From the FAPESP Scientific Initiation project of the same name.

  5. Exploring Simplicity and Efficiency: Regression-based Scheduling Heuristics in HPC

    Rosa, L., Carastan-Santos, D., & Goldman, A.

    Proceedings of the 14th Regional School of High-Performance Computing of São Paulo. pp. 41–44. Porto Alegre: SBC.

    10.5753/eradsp.2023.232635

  6. 2022

    In search of efficient scheduling heuristics from simulations and Machine Learning

    Rosa, L., & Goldman, A.

    Companion Proceedings of the 23rd Symposium on High Performance Computing Systems. pp. 17–24. Porto Alegre: SBC.

    10.5753/wscad_estendido.2022.226323

    Honorable mention at the Undergraduate Research Workshop (WSCAD-WIC), 2022.

Scholarships

  1. Sep 2026 – Aug 2027

    FAPESP Research Internship Abroad (BEPE-DD)

    Sustainable Supercomputing: Energy Efficiency and Resource Management through Statistical Modeling and Machine Learning

    Enhance supercomputing resource management using machine learning and optimization techniques with an emphasis on energy-aware scheduling.

    Principal Investigator
    Alfredo Goldman vel Lejbman
    Grant
    23/09048-8
  2. Sep 2024 – Feb 2026

    FAPESP Doctorate (DD)

    Sustainable Supercomputing: Energy Efficiency and Resource Management through Statistical Modeling and Machine Learning

    Enhance supercomputing resource management using machine learning and optimization techniques with an emphasis on energy-aware scheduling.

    Principal Investigator
    Alfredo Goldman vel Lejbman
    Grant
    23/09048-8
  3. Aug 2023 – Aug 2024

    CAPES Doctorate (DD)

    Academic Excellence Program (PROEX)

    Scholarship obtained through academic merit to support my doctorate research.

  4. Feb – Apr 2023

    FAPESP Research Internship Abroad (BEPE-IC)

    Evaluating machine learning techniques and simulations to create efficient scheduling heuristics

    Collaboration with the DATAMOVE research group to investigate regression methods to create simple and efficient scheduling heuristics.

    Principal Investigator
    Alfredo Goldman vel Lejbman
    Supervisor
    Denis Trystram
    Co-supervisor
    Danilo Carastan-Santos
    Grant
    22/14673-6
  5. Jul 2022 – Aug 2023

    FAPESP Scientific Initiation (IC)

    On limits of Machine Learning techniques in the learning of scheduling policies

    Explore the emerging relationship between managing resources on high-performance computing (HPC) platforms and the use of regression-derived scheduling heuristics to optimize performance.

    Principal Investigator
    Alfredo Goldman vel Lejbman
    Co-supervisor
    Danilo Carastan-Santos
    Grant
    22/06906-0
  6. Aug 2020 – Dec 2021

    FAPESP Technical Training (TT-1)

    Technical training in numerical methods and administration of computational resources

    Training in the management of high-performance computing systems and introduction to numerical methods relevant to scientific computing, particularly in the area of molecular simulation.

    Principal Investigator
    Guilherme Menegon Arantes
    Grant
    20/09918-4

Teaching experience

  1. Mar – Jul 2025

    Introduction to Computing for Exact Sciences and Technology

    Universidade de São Paulo · Alfredo Goldman

    Teaching assistant for undergraduate course. I taught a few classes and created homework assignments for a class of 70 students.

    70students, undergraduate

  2. Aug – Dec 2024

    Concurrent and Parallel Programming

    Universidade de São Paulo · Alfredo Goldman

    Teaching assistant for graduate-level course. I taught a few classes and created homework assignments for a class of 90 students.

    90students, graduate

Honors & awards

  1. 2023

    Brazil’s top 10 Scientific Initiation (IC) project

    Undergraduate Research Contest (CSBC-CTIC)

    Work selected as one of the 10 best scientific initiation works of 2023 according to the Brazilian Computer Society (SBC).

  2. 2022

    Honorable Mention

    Undergraduate Research Workshop (WSCAD-WIC)

    Awarded for the paper “In search of efficient scheduling heuristics from simulations and Machine Learning”.

Languages

  • Brazilian PortugueseNative speaker
  • EnglishAdvanced
  • FrenchBasic
  • SpanishBasic