Research Scientist - Speech Synthesis
Santa Monica, CA 90401
Science – Research Science /
Flawless is an award winning film technology company pioneering the generative AI revolution in filmmaking. Solving some of the biggest problems filmmakers face by empowering them with groundbreaking AI powered post production tools, allowing on screen dialogue to be visually changed without the need to reshoot or go back to set. The world’s first system has won multiple awards including TIME Best Inventions.
Founded in 2020 by Hollywood director, Scott Mann and serial technology entrepreneur Nick Lynes, Flawless is opening a world of new possibilities for filmmakers whilst ensuring the responsible adoption of generative AI. With headquarters in London and LA, Flawless has established an exceptional team of 100 world leaders in science, film and technology that have come from the likes of Adobe, Google, Lionsgate, NASA, Sony, Facebook, Microsoft and Apple (click here to find out more).
Flawless are looking for a smart, motivated, and committed Research Scientist for our Speech Synthesis team out of the LA Office. In this role, you will be working in an environment based on trust, autonomy and collaboration, and this is a great opportunity for someone who wants to be part of a growing company in its most exciting stage of development. You will have the ability to have immense impact on the company's suite of generative AI tools for VFX, focused on using and innovating the state of the art techniques in speech synthesis, audio visual speech modeling, and multi-lingual audio synthesis.
As a Research Scientist on the science team at Flawless, you will work with and lead a close-knit, passionate group of world-class individuals to tackle some of the most challenging problems in generative speech synthesis, accent modeling, and voice conversions. Our work in automated visual translation is just the beginning, we’re developing countless exciting products based on the application of our proprietary, cornerstone research.
- Minimum Qualifications
- Ph.D. or Postdoctoral researcher in audio synthesis, speech processing, or related field.
- 3+ years of experience with audio synthesis techniques such as TTS (Text-to-Speech), SST (Speech-to-Speech translation), or voice conversion methods.
- Demonstrable research experience with a strong publication record in major Speech Synthesis, Speech Processing at venues such as ICASSP, Interspeech, or NeurIPS.
- Proficiency in linear algebra, deep learning, and numerical optimization.
- Proficiency in Python, PyTorch, or Tensorflow.
- Proficiency in compute platforms such as GCP or AWS.
- Preferred Qualifications
- Experience with audio identity embedding, accent modeling, style-transfer, multi-language audio synthesis.
- Experience with attention, diffusion models and speech signal processing.
- Autonomy - You'll own your work from start to finish
- Influence - You'll impact major research decisions
- Publication - You’ll be encouraged to publish your work
- Learning - You’ll push the state-of-the-art with the best in the world
- Impact - Your input genuinely matters
- Stock Options
- Comprehensive medical, dental, and vision insurance
- 401(k) plan
Flawless is proud to emphasize an equal opportunity, safe environment for people to do their best work. We are committed to providing equal employment opportunities regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity, or Veteran status. We also consider qualified applicants regardless of criminal histories, consistent with legal requirements.