Job Description

• Bengaluru, Karnataka, India

At Murf AI, we're simplifying multimedia creation by harnessing the power of artificial intelligence. Our platform empowers users to craft high-quality voiceovers effortlessly, without the need for recording equipment.

Some interesting facts about Murf AI:

• Customers in 100+ countries
• 1Mn+ registered users
• 6X growth in revenue in last 12 months
• 120+ voices in 20+ languages offered by Murf Studio
• We’ve been consistently rated a Leader and Momentum Leader on G2 in the text-to-speech category in 2023 and 2022
• We are working on bleeding-edge research problems, in synthetic speech, synthetic video and dubbing

Job Summary:

We are seeking a highly skilled and innovative Research Scientist specializing in Generative Video AI to join our dynamic team. As a Research Scientist, you will play a pivotal role in developing cutting-edge algorithms and models for creating synthetic videos, avatars, and lip syncing applications. Your expertise in AI, computer vision, and image processing will be instrumental in advancing our technology and pushing the boundaries of generative video AI. This is an exciting opportunity to work at the forefront of AI research and contribute to groundbreaking advancements in the field.

An ideal candidate will hold a Ph.D. in AI or Computer Science with a specialization in Computer Vision, Image Processing, or related fields with 3+ years of additional relevant work experience.

Roles & Responsibilities:

• Conduct research in the field of generative video AI, focusing on synthetic videos, avatars, and lipsyncing use-cases
• Develop algorithms and models based on state-of-the-art computer vision and machine learning advancements, especially in the areas of generative AI (e.g. image, video, or 3d generation)
• Collaborate with cross-functional teams to understand requirements, identify research problems, and propose innovative solutions
• Collect and curate large-scale datasets for training and evaluating video generation models
• Develop and optimize computational pipelines for video generation, ensuring efficiency and scalability
• Stay up-to-date with the latest advancements in generative video AI, attending conferences, publishing research papers, and actively contributing to the scientific community
• Provide technical guidance and mentorship to junior researchers and engineers
• Collaborate with product teams to integrate research findings into practical applications and drive commercialization efforts
• Contribute to patent filing and intellectual property protection activities, as applicable

Skills & Qualifications:

• Strong background in generative models, deep learning such as GANs, NeRFs, VAEs, Diffusion Models etc
• Solid understanding of image processing and computer vision techniques in general
• Ability to conduct original research and first principles problem solving
• Ability to collaborate effectively in a team environment and lead research initiatives
• Proficiency in programming using Python and either TensorFlow or PyTorch
• Proven publications in computer vision or artificial intelligence peer-reviewed top tier conferences (e.g. CVPR, ECCV, ICCV, NeurIPS, ICLR, or SIGGRAPH, etc) or leading Journals (LNCS, PAMI, TOG etc.) published by IEEE, ACM, Springer, Elsevier etc.
• Experience with large-scale data collection and curation is a plus