Research Scientist - Speech

As a Research Scientist at Murf AI, you will be responsible for designing, implementing, training, benchmarking, and deploying deep learning models to create innovative solutions for users. You should be able to implement industry research papers and come up with proprietary research in the generative media domain, specifically speech synthesis. The ideal candidate will hold a Ph.D. in AI, Computer Science, or Electrical Engineering with a specialization in Audio, Speech, Signal Processing, or related fields and have at least 3 years of relevant work experience. **Key Responsibilities:** - Designing and developing new algorithms for media synthesis, speech recognition, speech enhancement, filler word detection, etc. - Writing performant and clean code for ML training. - Independently running and analyzing ML experiments to diagnose problems and understand real improvements. - Collaborating closely with a small team to balance flexibility and iteration speed in research. - Creating realistic voice-doubles using only a few minutes of audio. - Devising and implementing fast and robust algorithms for spectrogram inversion. - Coming up with new research directions to improve the product. **Qualifications Required:** - Proven experience in implementing and iterating on deep learning algorithms. - Publications at top ML/Speech conferences are a plus. - Strong knowledge and experience of Python, PyTorch, Kaldi. - Proven ability to conduct original research and first principles problem-solving.,