I need a hands-on engineer who already speaks the language of generative AI and cloud, yet is still curious enough to pick up anything new I throw your way. The immediate mission is to squeeze more performance and reliability out of my production stack. Scope • Audit our current machine-learning models, pinpointing the quickest accuracy or latency wins. • Review AWS and Azure configurations—storage, networking, autoscaling—and flag obvious cost or speed bottlenecks. • Profile the Python codebase and LangChain / LangGraph pipelines, then suggest lightweight refactors or AutoGen prompts that remove friction. Deliverables (initial phase) 1. Concise findings report highlighting the top three pain points in models, cloud setup, and application performance. 2. A prioritized action list with step-by-step fixes I can green-light. 3. Code or configuration snippets demonstrating at least one implemented improvement, committed to Git and paired with quick test results. Tech you’ll touch Generative AI (LLMs), Python 3.x, LangChain, LangGraph, AutoGen, AWS (EC2, S3, Lambda), Azure (Functions, Storage), basic DevOps tooling. I’ll stay closely involved, assign bite-sized tasks, and review your pull requests. If we click, there’s plenty more optimization work ahead. Show me prior examples—speedups, cost reductions, or clever LangChain workflows—and let’s get started.