Hugo B.

Key Skills

Software

Other

Top Subject Matter

Aerospace fluid dynamics

CFD surrogate modeling

machine learning for engineering simulation

Top Data Types

Document

Top Task Types

Fine-tuning

Question Answering

Freelancer Overview

2020 Internship in Fluid Dynamics and Machine Learning, ArianeGroup: development of a surrogate model based on CFD and m. Brings 7+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other. Education includes Doctor of Philosophy, INSA Toulouse / Institut de Mathématiques de Toulouse (2026) and Specialization Degree, Centrale-Supélec (2020). AI-training focus includes data types such as Computer Code, Programming, and Document and labeling workflows including Fine-tuning and Question Answering.

Labeling Experience

2022–2026 PhD in Applied Mathematics: Physics-informed machine learning methods for hydraulics and hydrology models

OtherFine-tuning

Conducted physics-informed machine learning research for hydrology and hydraulics applications, focusing on parameter identification from observed system behavior. Built and trained models that incorporate physical constraints to infer thousands of parameters automatically from data. This work involved creating training/learning pipelines using scientific datasets and simulation-informed objectives rather than human labeling. • Developed physics-informed neural network approaches for hydraulics/hydrology • Trained models for spatially distributed parameter identification • Used physics constraints to guide learning and reduce data requirements • Produced research outputs suitable for inverse problems in flood simulation

2022 - Present

2022–2024 Teaching Assistant, INSA Toulouse: tutorials and practical sessions in Data Assimilation, PDE and Fourier Analysis

DocumentQuestion Answering

Served as a teaching assistant delivering tutorial and practical sessions on data assimilation concepts and related mathematical methods. Supported students through structured instruction and guided exercises aligned with physics-based machine learning and inverse problem framing. While not explicitly an annotation role, this constituted AI/data-science training instruction in a technical domain. • Conducted practical sessions on data assimilation topics • Provided instruction on PDE and Fourier analysis for applied modeling • Assisted multi-year undergraduate curriculum learners (2nd to 5th year) • Helped students understand and apply analytical methods relevant to ML workflows

2022 - 2024

2020 Internship in Fluid Dynamics and Machine Learning, ArianeGroup: development of a surrogate model based on CFD and machine learning for Ariane 6

OtherFine-tuning

Developed and applied machine learning surrogate models to replace computational fluid dynamics (CFD) calculations for aerospace engineering use cases. Implemented model-driven learning workflows where training data originated from simulation outputs rather than manual human annotation. Focused on improving predictive accuracy and computational speed for downstream engineering decisions. • Built surrogate models using CFD-generated data • Trained and validated ML predictors for fluid dynamics tasks • Evaluated surrogate performance against reference simulation results • Produced outputs usable for faster engineering iterations

2020 - 2020

Education

Work History