AI Engineer for Automated Video App

PLEASE READ BEFORE APPLYING ‼️ I’m looking for an experienced AI engineer to help build the core feature of a mobile app that automatically converts lecture slides (PowerPoint or PDF) into engaging educational videos. The goal is similar to NotebookLM’s video overview concept, but focused on students and educational content. Desired User Flow 1. User uploads a PowerPoint or PDF lecture. 2. AI analyzes and understands the content. 3. AI generates an engaging, natural sounding script (not simply reading the slides verbatim). 4. AI generates human sounding voice narration. 5. AI uses slide images and generates additional supporting visuals when needed. 6. The system assembles everything into video lessons. 7. Long presentations should be broken into multiple shorter video segments (for example, 10–15 minute videos). 8. Final output is delivered as a ready to watch video Preferred Skills * Python * AI workflow development * LLM integration (OpenAI, Gemini, Claude, etc.) * Retrieval-Augmented Generation (RAG) * Remotion * FFmpeg * ElevenLabs or similar text-to-speech systems * PDF and PowerPoint processing * AI image generation APIs * Cloud deployment (AWS, GCP, Azure, etc.) * Experience building scalable AI applications