Senior Research Engineer at Antares Technologies

Location100% Remote. We hire anywhere within the U.S. Company OverviewAntares Audio Technologies is the pioneering force behind revolutionary audio processing solutions, including the industry-standard AutoTune pitch correction technology. For over two decades, we've been at the forefront of audio innovation, creating tools used by Grammy-winning artists, major recording studios, and content creators worldwide. We're seeking a talented Audio Machine Learning Engineer to join our R&D team and help define the next generation of intelligent audio processing technologies.Antares Audio Technologies is the leader in vocal enhancement software and maker of AutoTune, the best known brand in the music technology industry. AutoTune is a staple among professional singers, producers, and engineers with a near ubiquitous presence in production studios.About the PositionWe are looking for an experienced Audio Research Engineer to design, develop, and deploy cutting-edge machine learning models and signal processing for professional audio applications. You will work on challenging problems including intelligent pitch correction, formant shifting, vocal isolation, harmonic analysis, real-time audio effects, and next-generation creative tools for music production.Key ResponsibilitiesModel Development & ResearchDesign and implement deep learning models for audio signal processing, with focus on pitch detection, formant modification, vocal processing, and harmonic analysisDevelop solutions for source separation, vocal isolation, pitch correction, and intelligent audio effectsResearch and implement state-of-the-art techniques in music information retrieval and audio synthesisOptimize models for real-time performance in professional Digital Audio Workstation (DAW) environmentsData Engineering & Pipeline DevelopmentBuild robust data pipelines for processing large-scale music and vocal datasetsImplement audio preprocessing, pitch tracking, and spectral feature extraction techniquesDesign training infrastructure for models requiring high-quality audio dataDevelop automated model evaluation frameworks specific to music production quality metricsProduction & DeploymentDeploy ML models as VST/AU/AAX plugins and standalone applicationsEnsure ultra-low latency performance suitable for professional recording environmentsImplement A/B testing frameworks for audio quality assessment with professional usersMonitor model performance across different musical genres and vocal stylesCollaborate with plugin developers to integrate ML models into Antares' product suiteCross-functional CollaborationWork closely with product teams and professional audio engineers to understand musician and producer needsPartner with DSP engineers and audio researchers on breakthrough audio technologiesCollaborate with user experience teams to design intuitive interfaces for complex audio processingEngage with the music production community to gather feedback and validate new featuresRequired QualificationsEducation & ExperienceMaster's or PhD in Computer Science, Electrical Engineering, Machine Learning, or related field3+ years of experience in machine learning with focus on music/audio processing and professional audio applicationsStrong background in digital signal processing, music theory, and audio engineering fundamentalsTechnical SkillsProgramming Languages: Proficiency in Python; experience with C++ for performance-critical applications strongly preferredML Frameworks: Deep experience with PyTorch or TensorFlow, familiarity with specialized audio ML libraries (librosa, torchaudio, onnxruntime, ESPnet)Audio Processing: Expert understanding of pitch detection algorithms, spectral analysis, and time-frequency representationsDeep Learning: Hands-on experience with audio-specific architectures (WaveNet, CREPE, Tacotron) and generative modelsPlugin Development: Experience with VST/AU/AAX plugin development and real-time audio processingSoftware Engineering: Strong C++ skills for performance-critical audio applications, Python for ML developmentDomain KnowledgeDeep understanding of music theory, harmonic analysis, and vocal acousticsExperience with music production workflows and Digital Audio Workstations (Pro Tools, Logic, Ableton)Knowledge of audio plugin standards (VST, AU, AAX) and real-time audio constraintsFamiliarity with pitch tracking, source separation, and vocal processing techniquesPreferred QualificationsPhD in audio signal processing, music technology, or acousticsPublications in audio engineering conferences (AES, ICASSP, ISMIR, DAFx)Experience with generative audio models and neural audio synthesisBackground in music production or professional audio engineeringKnowledge of music copyright and licensing considerations for ML training dataExperience with cross-platform plugin development and optimizationTechnical EnvironmentLanguages: Python, C++, JUCE framework for audio applicationsFrameworks: PyTorch, TensorFlow, specialized audio ML librariesInfrastructure: On-premises high-performance computing clusters, cloud burst capabilitiesTools: Pro Tools, Logic Pro, Ableton Live, MATLAB, Jupyter, GitAudio Stack: JUCE, WebAssembly, Core Audio, iOS, professional audio interfacesWhat We OfferComprehensive health, dental, and vision insuranceAccess to world-class recording studios and professional audio equipmentFlexible work arrangementsPerformance bonusesUnlimited PTOPaid Federal holidays, including a week off for everyone at the end of the yearPaid Parental Leave4% 401k match after 6 monthsMusic production software licenses and professional development opportunitiesFull compensation packages are based on candidate experience. Compensation ranges are established using national benchmarking data and apply across all geographic locations within the United States.Antares is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, disability, sex, sexual orientation, gender identity or expression, age, national origin, veteran status, genetic information, union status and/or beliefs, or any other characteristic protected by federal, state, or local law.