Deep Learning Scientist - Python (3-9 yrs)

Responsibilities :

- Utilize cutting-edge DL techniques to develop advanced algorithms for neural rendering using Python and popular deep learning frameworks.

- Collaborate closely with a team of passionate researchers and developers to address complex challenges in deep learning, including multi-modal image synthesis, audio- visual data fusion and image/video transformation.

- Enhance the performance of products, ensuring high levels of accuracy, speed, and scalability, with guidance from senior team members.

- Integrate developed software, algorithms, and AI models into our products and services, working collaboratively with stakeholders.

- Maintain the software's security, reliability, and maintainability, following senior team members' guidance.

- Conduct thorough testing and validation to meet the desired performance objectives.

Requirements :

- Bachelor's or Master's degree in Computer Science, Engineering, or a related field.

- 3+ years of industry or research experience in deep learning and computer vision, focusing on areas such as computational photography, neural talking head synthesis, representation and synthesis of lifelike facial attributes, video synthesis, etc.

- Experience with self-supervised, few-shot, or zero-shot learning techniques for image synthesis, as well as domain adaptation techniques for face image synthesis.

- Strong understanding of Generative networks (for use-cases like Super-resolution, In painting, etc.) and state-of-the-art deepfake algorithms.

- Minimum 2 year relevant experience with generative networks like Transformers, GANs, Auto-encoders, Diffusion models, etc.

- Minimum 1 year experience with Vision Transformers

- Experience with Multi-modal image synthesis with audio-visual data

- Proficiency in Python programming and deep learning frameworks like PyTorch or TensorFlow, with at least 3 years of experience.

- Experience in developing scalable tools and solutions for real-world computer vision problems or visual effects.

- Exceptional problem-solving skills and the ability to work effectively in a team environment.

Bonus :

- MS or Ph.D. in Visual Computing, Computer Vision, Machine Learning, or related field

- Experience with 3D GANs for human body/ face synthesis.