OPEN POSITION

Machine Learning Engineer TTS

We are now expanding our team and are looking for skilled, goal-oriented MLE to join our teams.

Apply now

Responsibilities

Design and optimize TTS models to ensure our voice assistant sounds as natural and accurate as possible

Collaborate closely with product managers and engineers to integrate TTS tech, making it seamless and intuitive for users

Partner with data teams to build efficient audio data pipelines, from speaker recording/preprocessing to model training

Regularly update and refine TTS models to adapt to various accents, dialects, and speech styles, enhancing user satisfaction and responsiveness

Keep up-to-date with the latest TTS advancements, bringing in innovative techniques and tools to keep us at the forefront of voice-assisted banking

Rigorously test and validate models to meet strict standards.

Requirements

Proficiency in Python and deep learning frameworks (especially, PyTorch)

Strong understanding of speech synthesis processing techniques

Experience with Fast Attention-Based Models: (FastPitch, FastSpeech 2) and modern variative approaches: (e.g., VITS, Glow-TTS)

Strong understanding of techniques to control prosody, rhythm, and emotional tone for expressive speech synthesis

Knowledge of normalization techniques, FSTs, NN for normalization

Familiarity with TTS evaluation techniques, including MOS and A/B testing

Familiarity with vocoder models (e.g. Vocos, HiFi-GAN, mimi)

Knowledge of signal processing, statistical modeling, and language structure.

What we offer

Rapid career progression, facilitated by our team of seasoned senior professionals who hail from prestigious, industry-leading companies

Remote work opportunities from Europe

Company has prominent clients with an opportunity for you to work on different projects and/or to be involved in developing our proprietary own products

Competitive compensation in Euro/USD, surpassing market standards.

Responsibilities

Design and optimize TTS models to ensure our voice assistant sounds as natural and accurate as possible

Collaborate closely with product managers and engineers to integrate TTS tech, making it seamless and intuitive for users

Partner with data teams to build efficient audio data pipelines, from speaker recording/preprocessing to model training

Regularly update and refine TTS models to adapt to various accents, dialects, and speech styles, enhancing user satisfaction and responsiveness

Keep up-to-date with the latest TTS advancements, bringing in innovative techniques and tools to keep us at the forefront of voice-assisted banking

Rigorously test and validate models to meet strict standards.

Requirements

Proficiency in Python and deep learning frameworks (especially, PyTorch)

Strong understanding of speech synthesis processing techniques

Experience with Fast Attention-Based Models: (FastPitch, FastSpeech 2) and modern variative approaches: (e.g., VITS, Glow-TTS)

Strong understanding of techniques to control prosody, rhythm, and emotional tone for expressive speech synthesis

Knowledge of normalization techniques, FSTs, NN for normalization

Familiarity with TTS evaluation techniques, including MOS and A/B testing

Familiarity with vocoder models (e.g. Vocos, HiFi-GAN, mimi)

Knowledge of signal processing, statistical modeling, and language structure.

What we offer

Rapid career progression, facilitated by our team of seasoned senior professionals who hail from prestigious, industry-leading companies

Remote work opportunities from Europe

Company has prominent clients with an opportunity for you to work on different projects and/or to be involved in developing our proprietary own products

Competitive compensation in Euro/USD, surpassing market standards.

© 2022—2024 Aiphoria

UK, Cyprus, Portugal, UAE