CV

Education

• Currently: Reliability Engineer (Intel)
• 2018-2021: PhD Degree, Computer Engineering (ASU, United States)
• 2017-2018: MS Degree, Computer Engineering (UFRGS, Brazil)
• 2013-2017: BS Degree, Computer Engineering (UFRGS, Brazil)

Work Experience

• Currently: Reliability Engineer @ Intel
  • I am currently working at Intel’s Advanced Reliability Characterization (ARC) group. My line of work involves extensive architectural knowledge for tracking fault propagation and conceiving mitigation strategies. My work is also very experimental in nature, as I am in charge of designing/running experiments as well as parsing/interpreting experimental data. For experiment design, I often write sets of scripts that interact with real-world equipment (i.e. motors, sensors, lasers) and collect data. Afterwards, such data is parsed and visualized using data-science libraries (i.e. pandas, scikit, plotly).
• 2018-2021: PhD Student / Research Assistant @ ASU
  • Worked on novel hardening techniques as well as on dedicated RHDB accelerator architectures for matrix multiplication and neural networks on FPGAs/ASICs. Particularly, thorough experimentation and a comprehensive analysis of multi-level fault models, my research aims to develop error detection/correction methods with minimum added costs (compared to traditional modular redundancy). Moreover, I have been involved in designing setups for beam experiments with FPGAs and with a fully custom chip, which integrates multiple different compute units and test structures. Additionally, I am currently involved in a project that focuses on efficient HW\SW co-design, in which accurate kernel identification enables optimal hardware acceleration decisions, for increased performance.
• Summer 2019: Intern / Student @ LANL
  • The experience at LANL was very unique, in the sense that I was able to do a lot of hands-on work with different types of radiation experiments (neutron generators for evaluating SEEs, gamma cells for evaluating TID effects, and laser sources for evaluating architectural vulnerabilities). At the same time, I have learned a lot from the theoretical stand point, as I have attended more than 50 hours of classes and lectures, from world-renowned researchers on a number of very relevant topics, ranging from particle physics, radiation testing methodologies, high-performance computing, space applications and beyond. Particularly, I have evaluated the impact of reducing the floating-point precision on neural networks in FPGAs, both in terms of accuracy and radiation sensitivity.

Download Full CV