Description

Design, optimize, and integrate speech and audio machine learning models into automotive infotainment middleware architectures.

This role is on-site.

Responsibilities

• Design, evaluate, and select ASR and TTS models for automotive systems.
• Incorporate tuned speech and audio models into the wider middleware software architecture.
• Develop training protocols and continuous improvement workflows for the software stack.
• Optimize audio and speech processing algorithms for performance.

Required Skills

• 5+ years of experience in Machine Learning and Deep Learning.
• Expertise in Speech Recognition (ASR) and Speech Synthesis (TTS).
• Hands-on experience with state-of-the-art ASR models (Kaldi, Wav2Vec, Whisper, or DeepSpeech).
• Knowledge of developing and evaluating TTS systems (XTTS, WaveNet, or Tacotron).
• Proficiency in Python and C/C++.
• Experience with PyTorch, TensorFlow, and Keras.
• Strong background in audio data processing and algorithm optimization.

Preferred Skills

• Effective written and verbal English communication skills.
• Degree in any graduate field.

Key Skills

Education

Any Graduate