Role Overview:
As an Audio Processing Engineer, you will lead the development of our innovative VoiceGuard™ feature. You will build the systems that can distinguish between a genuine customer and a deepfake voice, protecting our clients from emerging voice-based scams.
Responsibilities:
Design and implement algorithms for deepfake audio detection and voice biometrics (voice imprinting).
Process and analyze audio streams from call centers in real-time to identify suspicious indicators.
Research the latest advancements in audio processing and AI-driven voice synthesis to keep our defenses ahead of fraudsters.
Collaborate with the AI/ML team to build robust models for voice-based anomaly detection.
Qualifications:
For Full-Time: MS/PhD in a relevant field with 2+ years of experience in audio or speech processing.
For Interns: Currently enrolled in a Master of Science or PhD program in Electrical Engineering or Computer Science with a focus on Digital Signal Processing (DSP).
Strong background in audio signal processing, speech analysis, and machine learning.
Proficiency in Python and experience with audio processing libraries (e.g., Librosa, SciPy).