Audio AI Research Scientist – Audio Source Separation

This is a fully remote position, open to applicants in United States, +11 more locations.

📋 Description

• Conduct research, prototype, train, and assess innovative source separation and extraction algorithms for speech and various real-world sounds.

• Create strategies for processing single- and multi-microphone recordings, incorporating spatial cues and optional auxiliary sensors.

• Explore effective separation techniques in scenarios involving overlapping speakers, background noise, reverberation, and movement.

• Assess perceptual quality, separation efficiency, generalization, latency, memory usage, and computational needs.

• Work collaboratively with DSP and embedded software teams to implement models in real-time demonstrations and product platforms.

• Contribute to the development of patents and conference publications.

• Innovate next-generation algorithms that isolate, extract, or suppress specific sound sources from microphone recordings for real-time applications on physical devices.

⛳️ Requirements

• A graduate degree (MS or PhD) in machine learning, electrical engineering, computer science, or a related discipline, or equivalent research experience.

• Extensive hands-on experience in audio source separation, target sound extraction, speech enhancement, or similar neural audio processing.

• Strong foundation in audio DSP, time-frequency techniques, and microphone array or spatial signal processing.

• Experience in training and evaluating audio models using PyTorch.

• Proficiency in Python programming.

• Knowledge of objective and perceptual evaluation methods, as well as real-time low-power inference considerations.

• Ability to address complex, open-ended challenges that require experimentation.

• Familiarity with C/C++ is advantageous.

• Experience with multimodal or sensor-conditioned separation, ONNX/TFLite, or embedded deployment is a bonus.

• Strong communication abilities.

• Publications in conferences such as ICASSP, Interspeech, NeurIPS, or similar venues are appreciated but not mandatory.

🏝️ Benefits

• Bonus programs.

• Comprehensive health and welfare benefits.

• 401(k) plan.

• Exclusive perks aimed at enhancing wellbeing.

• Generous employee discount.

• Compensation that exceeds base salary.