Research Scientist, Text-to-Speech

1 hour, 56 minutes ago
Contract
Senior
Software Development
Oddin.gg

Oddin.gg

Oddin.gg is a top B2B esports betting provider, offering cutting-edge products like odds feeds and risk management to maximize profitability for partners worldwide.

Hotels, Restaurants & Leisure
51-250

Description

  • Research and train state-of-the-art text-to-speech models for realistic and emotional voice generation.
  • Experiment with different model architectures and datasets to improve TTS quality and inference speed.
  • Select the best-performing approaches and bring them into production.
  • Stay current with the latest research in speech synthesis and generative AI.
  • Generate new ideas for model and product improvements based on research developments.
  • Collaborate closely with a team of three TTS researchers.
  • Work with engineering and hardware teams to support deployment and production readiness.

Requirements

  • Experience training text-to-speech or voice cloning models.
  • Strong knowledge of transformers, diffusion models, and GANs.
  • Understanding of human speech and audio processing, including sampling, spectrograms, and vocoders.
  • Proficiency in Python and key ML libraries such as PyTorch and Hugging Face Transformers.
  • Ability to read research papers, implement approaches, and keep up with current literature.
  • Strong machine learning fundamentals and critical thinking skills.
  • Familiarity with modern speech synthesis models such as GPT-based, flow matching, Vevo, StyleTTS, IndexTTS, or MaskGCT is a plus.
  • Contributions to open-source AI tools or research publications in speech processing are a plus.
  • Familiarity with AWS or similar compute clusters is a plus.

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

Staff Research Scientist - Music

Spotify Media

Spotify is hiring a Staff Research Scientist for its Artist-First AI Music lab to advance generative music research and turn it into new listening experiences for artists and fans.

Computer Vision Machine Learning NumPy Python PyTorch
11 minutes ago

Principal Research Scientist - Music

Spotify Media

Spotify is hiring a Principal Research Scientist for its Artist-First AI Music lab to advance generative music technologies and create new listening experiences that deepen artist-fan connections.

Computer Vision Machine Learning NumPy Python PyTorch
1 hour, 11 minutes ago

Research Scientist/Engineer

Offchain Labs 11-50 Internet Software & Services

Offchain Labs is hiring a Research Scientist/Engineer to advance scalable, secure blockchain systems and help shape the next generation of Ethereum infrastructure.

Blockchain Ethereum
2 hours, 11 minutes ago

Founding Robot Learning Research Engineer

AVOMIND 11-50 Professional Services

A vertically integrated robotics company is hiring a founding research engineer to build the learning systems, data pipelines, and robot software that turn factory operations in Vietnam into dexterous automation.

Computer Vision PyTorch Reinforcement Learning
5 hours, 41 minutes ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers