Over the summer I learned what's actually happening behind that: how transformers process language through word embeddings, how temperature and probability shape outputs, how context windows fill and why responses vary between runs. I explored the full inference stack vLLM, LLM-d, model servers and learned how MaaS layers token metering and rate limiting on top to deliver AI as a managed service. I built AI skills that automate real workflows and learned that the model itself is only part of the equation the agents, skills, and prompting around it are what make it useful. I also studied where AI breaks down concept drift, inconsistent outputs across runs, token limitations which made you not just a better user of AI but a more critical one. AI is everywhere and most people use it without thinking about it. Now when you interact with any AI tool, you understand the mechanics behind it. Everywhere you hear about how "ai is going to take over" however that is not the case, how in some ways it still needs humans and I learned that during my internship at Red Hat. I am open to speaking about what I learned as Red Hat AI intern about generative AI and how it actually does impact a workplace environment, and how the world does still need software engineers.