Brett Plemons

About Brett Plemons

A decade-long journey from backend engineering to machine learning leadership has shaped my expertise in building production-scale ML systems that transform audio and speech data into intelligent experiences. As a Staff Machine Learning Engineer specializing in DSP, audio processing, and speech modeling, I architect and implement ML solutions that directly impact millions of users through speech-to-text, text-to-speech, and advanced speech-to-speech models.My technical evolution from hands-on development to ML engineering leadership reflects a deep passion for solving complex problems at the intersection of signal processing, machine learning, and distributed systems. I thrive on translating cutting-edge research in conversation dynamics, audio fingerprinting, prosodic patterns, and phonological features into robust, scalable production systems.Core ML Engineering Capabilities- Design and optimize end-to-end audio processing pipelines for STT/TTS applications- Architect production ML systems with comprehensive monitoring and performance tracking- Lead technical strategy for multi-phase ML projects across service boundaries- Build and maintain model repositories with versioning, governance, and reproducibility standards- Collaborate cross-functionally to identify technical blind spots and drive ML innovationRecent Technical Impact- Enhanced data ingestion efficiency by 86% through ML pipeline optimization- Reduced model inference error rates by 82% via advanced evaluation strategies- Accelerated model deployment cycles by 83% through MLOps improvements- Increased user engagement by 102% with speech model performance enhancements- Reduced cloud infrastructure costs by $500K annually through efficient resource managementMy approach combines deep technical expertise with strategic thinking, enabling me to tackle open-ended ML problems while mentoring teams and establishing best practices. I\'m passionate about pushing the boundaries of what\'s possible in audio ML, leveraging industry best practices and customer feedback to advance speech technologies that create meaningful user experiences.Currently focused on advancing speech synthesis and Speech-to-Speech models, I\'m always eager to collaborate on challenging problems in audio processing, conversation AI, and production ML systems.

Experience

1. Staff Machine Learning Engineer

   Propio Language Services

   Aug 2025 — Present · Overland Park, KS, US

   Leading ML engineering initiatives with focus on audio processing and speech modeling technologies. Architecting production-scale ML systems that deliver significant business impact through advanced speech-to-speech models, conversation dynamics analysis, and audio fingerprinting capabilities.Key Responsibilities- Design and implement end-to-end ML solutions for speech processing applications- Establish technical roadmaps for multi-phase ML projects delivering customer value- Build and maintain model zoo with comprehensive versioning and governance- Collaborate with cross-functional teams to identify technical opportunities and drive innovation- Optimize ML pipelines for performance, scalability, and cost-effectiveness- Mentor team members and establish ML engineering best practices across the organizationTechnical Focus Areas: Audio signal processing, speech synthesis, STT/TTS infrastructure, conversation AI, prosodic pattern analysis, and production MLOps systems.

Education

• Kansas State University

  Statistics and Data Science

• Southern New Hampshire University

  Bachelor of Science - BS, Computer Science

Skills

• Mobile Devices
• Team Leadership
• Catalysis
• Bacterial Culture
• Laboratory Skills
• Pipetting
• Troubleshooting
• Exhibit Preparation
• Business Development
• Sales
• Windows
• Bacterial Physiology
• Computer Hardware
• Entomology
• Customer Service
• Management
• Idea Person
• Python
• Optical Microscopy
• Social
• Networking
• Technical Support
• Gram Staining