If you are preparing for an ML or LLM engineering interview, or you want to finally understand how large models actually run in production, you are in the right place. In one focused session I will help you find your gaps, sharpen your resume and practise the questions interviewers really ask about KV cache, quantization, batching and serving. You leave with a clear plan, not just notes. A little about me. I am Harshal, an AI Software Engineer intern at Intel in Bengaluru and an M.Tech AI student at IIT Patna. This year I published two papers: a first-author paper at SemEval-2026 and a co-authored paper at SMM4H-HeaRD 2026. Before my master's, I spent 1 year 9 months at Beacon Healthcare Systems as a product engineer working on DevOps. I also won the Smart India Hackathon 2022 grand finale, placed in the top 10% of an AWS DeepRacer qualifier, and built TooBrief, an AI short-news app. Teaching is what I enjoy most. As a TA at IIT Patna I guided students through CS1101 programming tutorials and labs, and today I share what I learn with more than 13,000 people on LinkedIn. You do not need an IIT tag to do well here. Bring your questions, and let's build your plan together.