AI Machine Learning Engineer for Photo-to-Video Generation Application

Hello there, my name is Jack.

We are developing an AI powered platform that transforms static photos into cinematic videos with realistic camera movements such as push ins, pans, tilts and zooms. The system should intelligently analyze images and generate smooth, professional video clips that scale from 1080p to 4K.

We are looking for a skilled AI and ML Engineer with computer vision experience to help us research, develop, and deploy this technology.

Responsibilities
• Design and train models to convert photos into video sequences with natural movements
• Implement video rendering pipelines, starting at 1080p and later scaling to 4K
• Optimize generation speed and cost using efficient compute and cloud GPUs
• Build scalable infrastructure to handle batch video creation
• Collaborate on product integration into a web based platform
• Research and apply methods to improve realism and cinematic quality

Qualifications
• Experience in computer vision and deep learning using PyTorch, TensorFlow, or OpenCV
• Strong background in video synthesis, GANs, diffusion, or related AI techniques
• Familiarity with FFmpeg and video rendering pipelines
• Experience deploying ML solutions to the cloud such as AWS, GCP, or Azure
• Ability to balance speed and cost optimizations in video generation
• Strong problem solving and independent research ability

Nice to Have
• Prior experience with photo to video, animation, or image to video AI projects
• Familiarity with queue systems and batch processing for media
• Ability to contribute to full stack integration including APIs and SaaS platforms

How to Apply:
If this project excites you, we would love to hear from you. To apply, please include the following:
1. Relevant work samples such as links to your portfolio, GitHub, research papers, or demo projects, especially work related to photo to video, video synthesis, or computer vision
2. A short experience overview of three to five sentences about your background and why you are a strong fit for this role
3. A brief technical approach outlining how you might tackle the challenge of turning static images into cinematic video movements. This does not need to be detailed, just enough to show your thought process
4. Your current availability in hours per week and your preferred compensation model, either hourly or project based


Thank you for taking the time to review this opportunity. We are looking for someone who is not only highly skilled but also excited about pushing the boundaries of what is possible with AI generated media. If that sounds like you, we look forward to your application and the chance to build something groundbreaking together!