Machine Learning TTS Engineer

This is a fully remote position, open to applicants in Portugal.

📋 Description

• Expand TTS capabilities to new languages through the collection and curation of data, text normalization/G2P, and adaptation of models.

• Transition new TTS architectures from research to production by enhancing robustness, reducing latency, and improving quality, collaborating closely with MLOps on deployment.

• Advance existing models through post-training enhancements, data curation, architectural refinements, and innovative training methodologies.

• Develop efficient audio data pipelines from speaker recordings and preprocessing to model training.

• Create comprehensive benchmarks and evaluations to assess whether new model iterations are genuinely superior and understand the reasons behind their performance.

• Become part of a compact TTS team consisting of 2–3 ML engineers, supported by a dedicated MLOps team and a data engineer.

⛳️ Requirements

• Minimum of 3 years of experience in speech technology with practical TTS expertise.

• Hands-on experience with contemporary LLM-based TTS methodologies (e.g., VALL-E, CosyVoice, XTTS).

• Experience in preparing TTS models for production, focusing on stability, robustness, and inference efficiency at the model level.

• Proficient in deep learning frameworks, particularly PyTorch.

• Solid understanding of modern ML principles: Transformers, diffusion/flow matching, neural audio codecs, and vocoders.

• Knowledge of streaming TTS limitations (latency, chunked/incremental generation) and how they influence architectural decisions.

• Familiarity with audio signal processing and the linguistic aspects of TTS (phonetics, text normalization).

• Basic experience in processing speech data (segmentation, alignment, quality filtering).

• Acquainted with TTS evaluation techniques (MOS, SBS).

• Strong Python proficiency and sound software engineering practices.

• Demonstrated ability to independently investigate new concepts and enhance existing ML systems.

• BS or higher in Computer Science or a related discipline, or equivalent experience.

• Proficient in English at a B2 level or higher.

• Experience working with low-resource languages, including dataset creation and augmentation.

• Experience in designing recording scripts and specifications for TTS voice datasets.

• MLOps/DataOps experience, such as using MLflow, DVC, or similar experiment tracking tools.

• Proficient in C++.

• Publications in speech/ML venues are a plus.

🏝️ Benefits

• The team has developed award-winning AI products for technology corporations, including devices, voice assistants, and impactful products.

• Utilization of a cutting-edge tech stack: Speech Technologies, NLP, Generative AI (LLMs, diffusion models), and voice-first agentic architecture with a focus on privacy and on-premises deployment.

• High engineering standards and genuine ownership — the team prioritizes functionality in production over mere aesthetics in demos, allowing you to see the direct impact of your contributions.

• Rapid career advancement opportunities — a senior-heavy team and a plethora of real challenges facilitate faster growth than in other environments.

• Startup-like pace combined with enterprise-level stability — real clients, tangible revenue, and minimal bureaucracy.

• Fully remote positions available across Europe.

• 21 vacation days plus public holidays and 5 sick days.

• Private English lessons provided via Preply.