Applied Research Scientist

At the core of Hedra Studio is our Character-3 foundation model, the first omnimodal model in production. Character-3 jointly reasons across image, text, and audio for more intelligent video generation — it’s the next evolution of AI-driven content creation.

Note: At Hedra, we’re a team of hard-working, passionate individuals seeking to fundamentally change content and build a generational company together. You should have start-up experience and be a self-starter that is driven to build impactful products that change the status quo. You must be willing to work in-person in either NYC or SF.

Overview:

We are looking for an Applied Research Scientist with a specialization in model fine-tuning to join our team. This role involves taking our pre-trained 3DVAE and video diffusion models and adapting them to specific tasks or datasets to achieve optimal performance. The ideal candidate will have a deep understanding of transfer learning and fine-tuning techniques in the context of generative models.

Responsibilities:

• Fine-tune pre-trained 3DVAE and video diffusion models for specific applications, such as generating videos for particular AI agent tasks, ensuring adaptability to new datasets.
• Develop and implement strategies for efficient model adaptation, such as data augmentation or transfer learning, to optimize performance.
• Evaluate and compare the performance of different fine-tuned models, using metrics relevant to video generation.
• Collaborate with the research team to understand the requirements and objectives of each fine-tuning task, ensuring alignment with business needs.
• Document and communicate findings to the team and stakeholders, facilitating knowledge sharing and decision-making.

Qualifications:

• PhD or Master’s degree in Computer Science, Machine Learning, or a related field, with a focus on model adaptation.
• Strong background in deep learning, with a focus on generative models, and experience with model fine-tuning and transfer learning techniques, crucial for adapting models to new tasks.
• Proficiency in Python and deep learning frameworks like PyTorch or TensorFlow, essential for implementation.
• Excellent problem-solving and analytical skills, given the need to evaluate and iterate on model performance.
• Good communication and teamwork skills, as collaboration is key in a startup environment.

This role is focused on applying and refining existing models rather than developing new ones, ensuring practical deployment.

Benefits:

• Competitive compensation and equity
• 401k (no match)
• Healthcare (Silver PPO Medical, Vision, Dental)
• Lunch and snacks at the office

We encourage you to apply even if you don’t fully meet all the listed requirements; we value potential and diverse perspectives, and your unique skills could be a great asset to our team.