Research theme area:
Machine learning, denoising, flow, computational fluid mechanics, particle image velocimetry, neural networks, unsupervised machine learning methods.

Abstract:
The candidate will collaborate with researchers from the project 56 FAPESP Research Centre for Greenhouse Gas Innovation of POLI-USP at the University of São Paulo. Summary of the program and projects can be found at the RCGI website (https://sites.usp.br/rcgi/). The selected candidate will employ machine learning to perform flow analysis with a focus on noise removal, construction of neural networks and unsupervised methods. The candidate must work with experimental and numerical source data.

Description:
The applicant will contribute in line with the main objectives of the project:

1. Use advanced computational techniques and machine learning algorithms to analyze flows by removing noise, building neural network models and obtaining structures from unsupervised methods.
2. Work with flows obtained experimentally or CFD simulation.
3. Understand experimental and numerical methods related to fluid mechanics.
4. Collaborate closely with a multidisciplinary team of researchers to integrate their studies across diverse areas.
5. Being able to perform CFD simulations and experiments with optical techniques such as PIV.

Requirements to fill the position:
We are seeking a highly motivated candidate with a PhD in Engineering or field related, with solid experience in machine learning applied to fluid mechanics. A robust publication history, experience in multidisciplinary research environments, experience in industrial property production (patents and software registrations) are highly desirable. Proficiency in English is required.

INFORMATION ABOUT FELLOWSHIP:
This Postdoc Fellowship is funded by FAPESP. The fellowship will cover a standard maintenance stipend per month for PD (amount available at https://fapesp.br/valores/bolsasnopais).

MORE INFORMATION:
https://sites.usp.br/rcgi/opportunities/
Position: Post-Doctoral Fellowship REF.: 24PDR274

Access here AND APPLICATION AT REF Post-Doctoral REF.: 24PDR274