Simulation-based inference (SBI) algorithms open a pathway for scalable large-scale validation of predictive models in magnetic confinement fusion research (MCF) [1]. Computationally costly models, with a selection of uncertain input parameters, are ubiquitous within MCF [2 – 5]. Due to the input uncertainties, multiple forward passes are typically required in model validation to quantify the distribution of the input parameters that best reproduces the experimental observations [6]. Solving this inverse problem is a key challenge in model validation and must be done algorithmically, such as using SBI, in large-scale validation workflows. While data-efficient, inverse inference workflows have been demonstrated in model calibration applications within MCF [6 – 9], a large-scale adoption in model validation activities has not emerged yet. One of the entry barriers is the software infrastructure for large-scale applications, requiring custom solutions for distributed computing, database handling, and sorting out failed simulations within the workflow. However, these requirements align with those needed for data generation for general machine learning surrogate modelling of computationally expensive models [10]. Therefore, in this work, a scalable SBI framework is developed and presented, building on top of Enchanted-surrogates, originally designed for simulation data generation for surrogate models [10]. Application of this SBI framework for simulations of synchrotron emission pattern evolution in a JET plasma with argon induced disruption and runaway electron beam is presented. [1] K. Cranmer, et al. Proc. Natl. Acad. Sci. 117 (2020) 30055. [2] F. Jenko, et al. Phys. Plasmas 7 (2000) 1904. [3] S. Wiesen, et al. J. Nucl. Mat. 463 (2015) 480 – 484. [4] M. Hoelzl, et al. Nucl. Fusion 61 (2021) 065001. [5] M. Hoppe, et al. Comp. Phys. Commun. 268 (2021) 108098. [6] A.E. Järvinen, et al. J. Plasma Phys. 88 (2022) 905880612. [7] E. Crovini, et al. Phys. Plasmas 31 (2024) 063901. [8] I. Ekmark, et al. J. Plasma Phys. 90 (2024) 905900306. [9] I. Pusztai, et al. J. Plasma Phys. 89 (2023) 905890204. [10] https://github.com/DIGIfusion/enchanted-surrogates/