In this presentation, we will explore into the key aspects of aligning Large Language Models (LLMs) and explore how to set up the necessary infrastructure to maintain a versatile alignment pipeline. Specifically, we will cover: Incorporating LLMs into the data collection for supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to maximize efficiency. Techniques for instilling desired behaviors in LLMs with the use of prompt tuning. A cutting-edge workflow management approach, and how it facilitates rapid prototyping of highly-intensive distributed training procedures. This session is tailored for machine learning engineers who are deploying their LLMs and seeking to improve their models.