As a GenAI Intern, you will be responsible for developing cutting-edge models for end-to-end content generation, including AI-driven image/video generation, lipsyncing, and multimodal AI systems. You will work on the latest advancements in deep generative modeling to create highly realistic and controllable AI-generated media.
Selected intern's day-to-day responsibilities include:
1. Research & Develop: Design and implement state-of-the-art generative models, including Diffusion Models, 3D VAEs and GANs for AI-powered media synthesis.
2. End-to-End Content Generation: Build and optimize AI pipelines for high-fidelity image/video generation and lipsyncing using diffusion and autoencoder models.
3. Speech & Video Synchronization: Develop advanced lipsyncing and multimodal generation models that integrate speech, video, and facial animation for hyper-realistic AI-driven content.
Only those candidates can apply who:
1. are available for the work from home job/internship
2. can start the work from home job/internship between 11th Mar'25 and 15th Apr'25
3. are available for duration of 3 months
4. have relevant skills and interests
1. Experience working with deep generative models, including Diffusion Models, 3D VAEs, GANs and autoregressive models.
2. Strong proficiency in Python and deep learning frameworks such as PyTorch.
Expertise in multi-modal AI, text-to-image, and image-to-video generation, audio to lipsync.
3. Background in text-to-video generation, lipsync generation and synthetic media applications.
Pixell is an enterprise that works on stealthy ideas related to generative AI and large language models.
