CV 2-pages CV

Work

  • 2024.09 - 2024.12
    Research Intern
    Google DeepMind
    Researching video segmentation with a focus on SAM 2, supervised by Stefano Pellegrini, Jasper Uijlings, and Cordelia Schmid.
  • 2024.06/01 - 2024.08
    Guest PhD student
    Technical University of Munich and Helmholtz Munich
    Conducted research on multi-modal large language models and audio-visual learning under Prof. Zeynep Akata and assisted with teaching a graduate seminar.
  • 2023.07 - 2024.03
    Research Intern + Student Researcher
    Google Research
    Led research on efficient adaptation of large-scale models under the guidance of Anurag Arnab, Alexey Gritsenko, and Cordelia Schmid. Collaborated with Aleksandra Nowak, Utku Evci, Yann Dauphin from Google DeepMind, driving key innovations in model adaptation.
  • 2020.11 - 2021.04
    Machine Learning Researcher
    Everseen
    Researched ways of improving tracking systems in real-time multi-camera scenarios
  • 2018.07 - 2018.09
    Junior Software Engineer
    Presslabs
    Successfully contributed to the development of the open-source MySQL operator for Kubernetes.
  • 2017.06 - 2017.09
    Junior Software Engineer
    3Pillar Global
    Successfully refactored and optimized critical components of the software and identified and resolved bugs to improve overall performance. Worked in the Decision Lens team.
  • 2017.02 - 2018.06
    Undergraduate Research Assistant
    DSPLabs research group at Politehnica University of Timisoara
    Selected to develop an interface for the FENP real-time scheduling algorithm collaborating with Cristina and Valentin Stangaciu.

Education

  • 2021.05 - 2024.08

    Tübingen, Germany

    PhD
    Max Planck Institute for Intelligent Systems and University of Tübingen
    Computer Science
  • 2019.09 - 2020.08

    Edinburgh, UK

    MSc
    University of Edinburgh
    Artificial Intelligence
  • 2015.10 - 2019.06

    Timisoara, Romania

    BEng
    Politehnica University of Timisoara
    Computers and Information Technology

Interests

Artificial Intelligence
zero-shot and few-shot learning
efficient adaptation for large-scale models
audio-visual learning in the video domain
multi-modal large language models
video semantic segmentation
object detection and tracking