Digital Signal Processing Engineer

Summary

Ribbon is looking for a Digital Signal Processing Engineer with rich hands-on experience and strong technical expertise to design, develop, and implement advanced Digital Signal Processing (DSP), Machine Learning (ML), and Deep Learning solutions for voice security, cybersecurity, and voice fraud prevention.

In this role, you will research, develop, and deploy solutions that leverage speech processing, signal analysis, machine learning, and deep learning to address challenges such as synthetic voice detection, audio deepfake detection, speaker verification, Automatic Speaker Verification (ASV) spoofing detection, voice authentication security, and fraud detection.

You will be responsible for end-to-end software development, including requirements discussions, design, implementation, model development, testing, deployment, and collaboration with architecture and test teams across multiple geographies.

Responsibilities

· Conduct innovative research in Digital Signal Processing (DSP), Machine Learning, Deep Learning, and Speech Processing technologies to develop solutions for voice security, fraud prevention, and cybersecurity applications.

· Design, develop, train, and optimize machine learning models for:

o Synthetic voice and audio deepfake detection

o Text-to-Speech (TTS) generated speech identification

o Automatic Speaker Verification (ASV) spoofing detection

o Speaker authentication and voice biometric security

o Fraud detection and anomaly detection

· Apply Digital Signal Processing (DSP) techniques to analyze, preprocess, enhance, and extract meaningful information from speech and audio signals.

· Design and develop feature extraction pipelines leveraging techniques such as FFT, spectrograms, Mel-spectrograms, MFCCs, LFCCs, cepstral analysis, and speaker embeddings.

· Research, develop, and evaluate advanced countermeasures against synthetic speech, voice deepfakes, and ASV spoofing attacks using state-of-the-art machine learning and deep learning techniques.

· Analyze large-scale speech, audio, and security datasets to identify meaningful patterns, emerging threats, and actionable insights.

· Develop algorithms that combine signal processing and machine learning techniques to improve detection accuracy and robustness against evolving voice-based attacks.

· Write clean, maintainable, and high-performance code using modern programming languages and AI/ML frameworks. Debug, troubleshoot, and resolve software defects efficiently.

· Work closely with cross-functional engineering, architecture, product, and security teams to integrate AI/ML solutions into existing and next-generation Ribbon products.

· Stay current with advancements in speech processing, digital signal processing, machine learning, deep learning, voice biometrics, and audio security technologies.

Requirements

· Degree in Computer Science, Electrical Engineering, Computer Engineering, Signal Processing, Speech Processing, Artificial Intelligence, Data Science, or a related field with 5-8 years of rich industry experience or PhD. (Candidates with research experience and/or with Published research papers would be preferred)

· Demonstrated proficiency in Python and/or C/C++/GOLANG, and hands-on experience with machine learning and deep learning frameworks such as PyTorch, TensorFlow, Scikit-learn, NumPy, Pandas, and Jupyter Notebook.

· Experience developing, training, and optimizing machine learning and deep learning models for speech, audio, voice biometrics, signal classification, cybersecurity, or related applications.

· Strong understanding of Digital Signal Processing (DSP) and speech processing concepts, including:

o Sampling Theory and Signal Reconstruction

o Time-Domain and Frequency-Domain Analysis

o Fourier Transform (FFT) and Spectral Analysis

o Digital Filtering and Noise Reduction

o Feature Extraction Techniques (MFCC, LFCC, Spectrograms, Mel-Spectrograms, Speaker Embeddings)

o Text-to-Speech (TTS)

o Speaker Recognition and Verification

o Voice Biometrics

o Speech Embeddings

o Synthetic Speech and Audio Deepfake Detection

o ASV Spoofing and Anti-Spoofing Techniques

· Familiarity with state-of-the-art speech AI and anti-spoofing architectures such as CNNs, Transformers, Conformers, ECAPA-TDNN, RawNet, AASIST, Wav2Vec 2.0, and related models used for speaker verification, synthetic speech detection, and ASV spoofing countermeasures.

· Experience applying DSP techniques to speech, audio analytics, voice authentication, or signal classification problems.

· Strong understanding of machine learning fundamentals, deep learning techniques, statistical modeling, data structures, algorithms, and computational complexity.

· Experience evaluating model performance, conducting experiments, and analyzing large-scale datasets to derive meaningful insights.

· Strong analytical and problem-solving skills with the ability to thrive in a highly collaborative and fast-paced environment.

· Excellent communication skills with the ability to translate complex technical concepts and findings into actionable insights for various stakeholders.

Preferred Qualifications

· Experience working with speech and audio processing toolkits and frameworks such as Hugging Face, SpeechBrain, Kaldi, PyTorch Audio, OpenSMILE, or similar technologies.

· Experience with speech and audio datasets, ASVspoof challenge datasets, speaker verification systems, voice authentication technologies, and Text-to-Speech (TTS) models.

· Knowledge of voice biometrics, audio deepfake detection, speaker authentication systems, synthetic speech detection, and fraud prevention technologies.

· Experience with audio feature extraction techniques including MFCC, LFCC, CQCC, spectrograms, filter banks, x-vectors, and speaker embeddings.

· Familiarity with cybersecurity concepts, authentication systems, and AI/ML applications for security and fraud detection.

· Familiarity with Kubernetes, Docker containers, cloud platforms (AWS, Azure), virtualization technologies, and MLOps best practices.

· Industry experience applying machine learning and signal processing techniques to real-world voice security, fraud detection, cybersecurity, or enterprise AI challenges.

· Knowledge of advanced statistical techniques, experimentation methodologies, and data visualization tools.

The anticipated base pay range for this full-time position in all geographic locations is $120,000.00 - $170,000.00 annually. Actual compensation within the range will be determined based on a variety of factors, including, but not limited to the candidate’s experience, skills and education. The compensation package also includes eligibility for an incentive plan and comprehensive benefits, subject to applicable requirements.

Please Note:

'All qualified applicants will receive consideration for employment without regard to race, age, sex, color, religion, sexual orientation, gender identity, national origin, protected veteran status, on the basis of disability, or other characteristic protected by applicable law.'

US Citizens and all other parties authorized to work in the US are encouraged to apply.