Fotis Giasemis

Cern Association Lhcb @CERN

Paris, FR
MOBILE NUMBERS
+91 *********19

Signup · Get unlimited contacts

WORK HISTORY

Oct 2022 — Present

Cern Association Lhcb @CERN

View department →

Geneva, CH

Marie Sklodowska-Curie (Early Stage Researcher) PhD fellowship on High Energy Physics and Artificial Intelligence, as part of the SMARTHEP European Training Network, and in collaboration with the CERN LHCb experiment and Ximantis.\\\\n\\\\n• Project:\"ESR5: RTA on heterogeneous architectures for LHC and self-driving cars\"\\\\n\\\\n• Description: The goal of this project is to, in partnership with a number of computing hardware companies, train ESR5 in programming for heterogeneous computing architectures, and in simultaneously optimizing data formats and processing techniques to enable CPUs, GPUs, FPGAs, and hybrids to work together to solve problems which none of these technologies could solve on their own. The first objective of ESR5 will be to design a novel ML method for optimizing heterogeneous computing architectures, and deploy it in the context of the specific requirements of real-time data processing in the LHC collaborations. This method takes as input the cost of the various computing architectures under consideration, builds and emulates test processing systems, tests them using the task being optimized for and finds the most cost-effective one. The second objective will be to apply this optimization code to the specific problems of the LHCb and ATLAS real-time data-processing architectures. ESR5 will implement new deep learning models for decision-making in self-driving cars, using the HLS4ML code, supervised by Pierini at CERN. As the tools developed by ESR5 will be experiment-independent, they will be portable and useful for applications for other LHC and future experiments. Specifically, ESR5 will be able to use LHCb data as a test bench, and Open Data for other experiments. The secondment at XIMANTIS will allow ESR5 to test a specific kind of algorithms, Attention networks, to focus both traffic prediction and resource consumption algorithms to a limited number of features.\\\\n \\\\n\\\\n \\\\n \\\\n\\\\n \\\\n

EDUCATION

N/A

University of Oxford

MMathPhys, Mathematical and Theoretical Physics

N/A

Sorbonne University

PhD, High Energy Physics

N/A

National Technical University of Athens

MSc, Applied Mechanics

SKILLS

EnglishC++PhotoshopMicrosoft ExcelSocial MediaPowerpointMicrosoft OfficeTeamworkCustomer ServicePublic SpeakingMicrosoft WordResearch

ABOUT FOTIS GIASEMIS

Oxford Theoretical Physics graduate, currently Marie Curie PhD Fellow at Sorbonne/CERN, with a strong background in mathematical modeling and machine learning. Expertise in high-frequency data analysis, real-time ML on GPUs and FPGAs, and high-performance computing with C++ and Julia. Experience in time series anomaly detection and forecasting with ML, deploying and backtesting quantitative trading strategies, and stochastic processes. Transitioning expertise to financial markets, alpha research, volatility modeling, and market microstructure research. For more, visit my personal page: fotisgiasemis.com.

This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.

Fotis Giasemis — Cern Association Lhcb at CERN in Paris, FR | Unifers