Senior Audio AI Engineer

Senior Audio AI Engineer focuses on inspect, maintain, repair, install, design, or improve technical systems according to the role.

What the role involves

• Inspect, maintain, repair, install, design, or improve technical systems according to the role.
• Diagnose issues, complete checks, and keep records or handovers accurate.

Skills and requirements

• Experience with transformer-based models for speech synthesis and NLP.
• Experience in designing scalable AI-driven applications.
• 3+ years of experience developing and deploying TTS or speech generation systems (bonus for low-resource languages).
• Experience with audio processing tools (e.g., librosa, Praat, torchaudio).

Confirmed role details

• Optimize neural TTS models for prosody, pacing, and expressiveness (e.g., Tacotron 2, FastSpeech 2, Glow-TTS, VITS).
• Implement and fine-tune transformer-based architectures for speech synthesis and text-to-speech tasks.
• Optimize speech processing pipelines for efficiency and real-time performance.
• Lead both objective (e.g., duration errors, pitch contours) and subjective (e.g., MOS scoring) evaluations of TTS quality.

Candidate fit

• technical judgement, safe working habits, careful diagnostics, and practical problem-solving