Developed dynamic resource limit functionality for the AI-Hypercomputer/xpk repository, focusing on Kueue and Jobset controllers within Kubernetes environments. Leveraged Python and YAML to implement auto-calculated memory limits based on cluster node count, updating both new and existing scripts to automate resource allocation. This approach reduced the need for manual tuning as clusters scale, enhancing the reliability and throughput of job orchestration workloads. The work emphasized cloud infrastructure management and shell scripting to ensure controllers consistently receive adequate resources, resulting in improved deployment stability and scalability. No explicit bugs were documented, reflecting a focus on proactive automation and system robustness.