We are looking for a passionate and skilled developer to build an AI-powered video editing tool that helps users organize, search, and generate stories from their personal video footage. This tool will leverage speech-to-text, NLP, and video processing technologies to provide a seamless storytelling experience for creators.
Responsibilities of the Candidate:
- Design and develop a full-stack application for uploading, processing, and editing personal video content.
- Implement AI transcription using tools like OpenAI Whisper or other speech-to-text APIs.
- Develop intelligent search functionality to find key moments based on user queries and transcript content.
- Create an automated storytelling feature that stitches relevant clips into coherent narratives based on prompts or topics.
- Build a clean, intuitive frontend interface for users to interact with their footage and AI-generated stories.
- Optimize backend systems for video rendering, storage, and real-time response.
- Deploy and maintain the application using cloud platforms (e.g., Vercel, AWS, or Streamlit).
Requirements:
- Languages & Frameworks: Python, JavaScript, React.js, Node.js or FastAPI
- Video Processing: FFmpeg, MoviePy
- AI/NLP: OpenAI Whisper, speech-to-text APIs, basic NLP, prompt engineering
- Search & Indexing: Transcript parsing, vector search (e.g., FAISS)
- Cloud & Storage: AWS S3, Firebase, cloud deployment platforms
- Others: Git/GitHub, REST API development, UI/UX for video tools, media metadata handling
