Efficient memory allocation is critical for controlling and optimizing High-Performance Computing (HPC) infrastructures. This action design research study aims to identify the best principles, practices, and patterns for improving the precision and efficiency of control and optimization mechanisms in large-scale HPC infrastructure. To achieve this, we explore the use of Artificial Intelligence Operations (AIOps), which applies artificial intelligence to manage software infrastructure operations. In this context, we propose Job Prophet (JP), a machine-learning-based application. JP is designed to regulate and continuously optimize HPC resource management, enhancing operational efficiency and performance. The tool integrates continuous training, inference, monitoring, and CI/CD pipelines, ensuring adaptability to dynamic workloads. By leveraging historical execution data from heterogeneous sources, JP enhances scheduling efficiency while maintaining model reliability through continuous retraining and monitoring. We evaluate JP on real-world HPC workloads, demonstrating significant improvements in resource utilization and job performance. Our findings highlight the benefits of AI-driven memory allocation and provide insights into scalable, automated machine-learning integration within HPC environments.

This paper presents a systematic literature review (SLR) focused on the implementation of chatbots using Large Language Models (LLMs), aimed at providing insights into the architectures, frameworks, best practices, and evaluation metrics that are shaping the field. By analyzing 39 primary studies, the review addresses six key research questions, exploring common architectures such as client-server and Retrieval-Augmented Generation (RAG), and identifying frequently utilized models, including the GPT family, BERT, and open-source models like LLaMA. The paper evaluates the performance of these models across various domains, emphasizing the impact of fine-tuning, prompt engineering, and embedding techniques on accuracy and domain-specific relevance. Additionally, it highlights the critical evaluation metrics used in LLM-based chatbot systems, including accuracy, user satisfaction, content quality, safety, and efficiency. Ethical considerations, including data governance, bias mitigation, and fairness audits, are also discussed to ensure responsible deployment of LLM chatbots. The review concludes with an exploration of the trade-offs between performance, cost-efficiency, and scalability, providing a comprehensive framework for future research and development of LLM-based chatbot applications.

Companies are increasingly embracing cloud computing, and consequently, the need for effective methods and tools to manage their compute infrastructure also increases. However, managing complex and heterogeneous infrastructures remains a significant challenge, particularly in terms of observability, configuration consistency, and resilience. This PhD project aims to explore the integration of graph-based infrastructure visualization techniques to enhance infrastructure observability and management. The objective of the graph-based abstraction is to bridge the gap between architectural intent and operational reality, providing valuable support for monitoring, auditing, and failure analysis. We aim to address key infrastructure management issues such as configuration drift detection and remediation, and topology analysis.

Chaos Engineering (CE) has emerged as a proactive method to improve the resilience of modern distributed systems, particularly within DevOps environments. Originally pioneered by Netflix, CE simulates real-world failures to expose weaknesses before they impact production. In this paper, we present a systematic gray literature review that investigates how industry practitioners have adopted and adapted CE principles over recent years. Analyzing 50 sources published between 2019 and early 2024, we developed a comprehensive classification framework that extends the foundational CE principles into ten distinct concepts. Our study reveals that while the core tenets of CE remain influential, practitioners increasingly emphasize controlled experimentation, automation, and risk mitigation strategies to align with the demands of agile and continuously evolving DevOps pipelines. Our results enhance the understanding of how CE is intended and implemented in practice, and offer guidance for future research and industrial applications aimed at improving system robustness in dynamic production environments.