ML- Video

ImmverseAI is driven by seasoned technology leaders, serial entrepreneurs, startup founders and a diverse team of 25+ tech professionals from the Heart of India India & Silicon Valley, USA; driving cutting-edge innovation and shaping the future of humanity.

The challenge with global LLMs is them being deeply rooted in the Global North – ImmverseAI is democratizing and reducing the digital divide to achieve the goal of AI for All, in an equitable and responsible way.

• 1) Video Generation Model Development:
• Design and implement machine learning models for video generation, focusing on realism and creativity.
• Specialize in the development of talking head generation models for natural and expressive visual content.
• 2) Data Processing and Pre-processing:
• Collaborate with data scientists to pre-process and curate large video datasets, ensuring diversity and quality for training and evaluation.
• Implement data augmentation strategies for enhancing the realism and expressiveness of talking head models.
• Optimization and Scalability:
• Optimize video and talking head generation models for efficiency, scalability, and real-time processing.
• Work closely with infrastructure and DevOps teams to deploy models in production environments.
• 3) Research and Innovation:
• Stay abreast of the latest developments in video generation, talking head synthesis, and related fields.
• Contribute to research initiatives, experimenting with novel techniques to advance video and talking head generation capabilities.
• 4) Model Evaluation and Testing:
• Design and execute comprehensive testing protocols to evaluate the performance, realism, and robustness of video and talking head generation models.
• Analyze results and iterate on models to achieve continuous improvement.

• Remote working can be considered but candidates willing to relocate to Nagpur would be preferred.
• Bachelors in Computer Science, Machine Learning, or a related field but if you are a great problem solver, a dropout is also welcome.
• Proven experience in developing machine learning models for video generation, with a focus on talking head synthesis.
• Proficiency in machine learning frameworks such as Tensor Flow or PyTorch.
• Strong programming skills in Python and familiarity with relevant libraries and tools.
• Solid understanding of computer vision, deep learning, and video processing techniques.
• Experience with large-scale video data processing, annotation, and talking head datasets.
• Strong problem-solving skills and ability to work collaboratively in a team environment.