Research Assistant: Bayesian Modelling & JAX Software

Radboud International; Nijmegen; In loco; EUR 42.000 - 60.000; Tempo pieno

Vantaggi offerti da questo lavoro

1-year contract

Holiday allowance 8%

End-of-year bonus 8.3%

Extra annual leave (30 or 41 days)

Descrizione del lavoro

Radboud University is seeking a Research Assistant to work on Bayesian modelling in JAX and contribute to bamojax, an open-source Python toolbox for Bayesian modelling and model comparison. You will collaborate with the Uncertainty in Complex Systems lab to compare models and develop efficient search procedures for model variants.

The role focuses on robust statistical analyses and advancing scientific software, with weekly PI meetings and opportunities to contribute to state-of-the-art

Competenze

• MSc degree in computer science, data science, AI, applied mathematics or related discipline.
• Demonstrable experience with Python and implementing statistical or ML algorithms.
• Experience with software development practices such as testing and version control with Git.
• Strong mathematical background in probability, statistics, calculus and linear algebra.
• Good communication skills.
• Passion for improving the scientific process.
• Prior experience with Bayesian statistics and/or JAX is a plus.

Mansioni

• Implement advanced methods for Bayesian model comparison in JAX.
• Construct an efficient search procedure for variants of a given model.

Conoscenze

Python

Statistical algorithms

ML algorithms

Communication skills

Mathematical background

Bayesian statistics

JAX experience

Testing and version control (Git)

Formazione

MSc in computer science, data science, AI, applied mathematics or related discipline

Strumenti

Git

JAX

Descrizione del lavoro

Radboud University is seeking a Research Assistant to work on Bayesian modelling in JAX and contribute to bamojax, an open-source Python toolbox for Bayesian modelling and model comparison. You will collaborate with the Uncertainty in Complex Systems lab to compare models and develop efficient search procedures for model variants.

The role focuses on robust statistical analyses and advancing scientific software, with weekly PI meetings and opportunities to contribute to state-of-the-art