On February 1st, 2010 I joined the oil and energy company Total in the Research & Scientific
Computing group. I am working as a project manager at the Scientific and Technical Center Jean
Féger (CSTJF), in Pau (South-West France). I am in charge of the conception and development of several
software for geosciences, more specifically: geostatistics and geomodeling, design of experiments for
reservoir engineering, seismic processing, petro-elastic modeling. Those complex software challenge IT systems
and technologies in terms of performances, architectures, efficiency, and availability.
Before that and since April 1st 2008, I worked in the IBM Tokyo Research Laboratory as a researcher.
I have been involved in the System Management & Compliance and in the Business Services Research
groups. My activity was centered on Business Process Management and its applications within emerging cloud
computing solutions. Clouds are highly dynamic structures in which underlying components must be capable of
handling rapid and frequent changes. My efforts permitted key components of cloud systems (provisioning and
asset management) to run highly customizable business processes thanks to a dedicated workflow extension
model. During 2009 I was invited to teach "Computer Science and Information
Systems" as part-time professor at Temple University in the Japanese campus.
I first arrived in Japan in November 2005 under the postdoc fellowship of the Japanese Society for the Promotion
of Science. I worked in the Tokyo Institute of Technology, with the guidance of Pr. Satoshi Matsuoka.
My research focused on autonomous grid applications based on peer-to-peer overlay networks. Ever-growing grids
make application development, administration, and maintenance more and more complex. Autonomic computing partially
answers these issues thanks to self-management mechanisms. Peer-to-peer networks assure scalability and robustness
of a system. Combined, they offer an efficient framework to build large grid applications. To illustrate this concept,
I developed an automated monitoring tool for large scale grids. I was especially concerned by fast and efficient information
propagation, by autonomous system dimensioning, and by fault-tolerance and self-recovery.
I got my PhD in Computer Science at the University of Nice Sophia-Antipolis in July 2005. I was working
at INRIA, the National Research Institute of Computer Science. My PhD advisors were Pr. Denis Caromel
and Dr. Françoise Baude. My PhD thesis deals about the critical importance of group communication for
high-performance and grid computing. While previous work on collective communications imposed the use of dedicated interfaces,
I proposed a scheme where one can initiate group communications using the standard public methods of the class. This mechanism
is then extended in an evolution of the classical SPMD programming paradigm. Object-Oriented SPMD provides interprocess
communications via transparent remote method invocations. The typed group pattern leads to an interesting, uniform, and
complete model for programming applications intended to be run on clusters and grids.