??Remote | ??? Audio Feature Engineering | ?? Speech & ML Analysis | ?? Python, Whisper, librosa | ?? Behavioral Data.

We're looking for an Audio ML Analyst – Speech & Timing to help us extract meaningful patterns from spoken audio. You'll work with tools like Whisper, PyDub, and librosa to analyze features such as pitch, latency, and silence gaps, supporting the development of machine learning models with behavioral insights.

?? Required Skills & Experience

• 3–5+ years of hands-on experience analyzing spoken audio (not necessarily call center — podcast, interviews, etc.).
• Knowledge of audio features like pitch, latency, filler words, interruptions, silence gaps.
• Comfortable using tools like Whisper, PyDub, librosa, Audacity, or similar.
• Can work with Python notebooks or scripts to extract and tag audio features.
• Good communication and attention to behavioral detail.

Do you think this could be a match? We'd love to hear about your experience. ??