Checkmate is the leading platform that connects restaurant POS systems with online ordering channels, automating workflows and enabling seamless order flow. We are now expanding into voice-driven ordering experiences through our Drive Through AI (DTAI) product line, which brings advanced AI and speech technologies to drive-thru lanes and phone ordering systems.
As a Senior Software Engineer (Audio & DSP), you will play a critical role in shaping the real-time speech processing stack for DTAI. This includes developing algorithms and systems that can perform reliably in noisy, multi-speaker, real-world environments. You will work at the intersection of digital signal processing, conversational AI, and restaurant operations, directly influencing technical architecture, prototyping, and product direction. Your contributions will impact how millions of customers interact with AI-powered voice systems in fast-paced restaurant environments.
Essential Job Functions
Algorithm Development & Optimization :
- Design, implement, and optimize real-time DSP algorithms for speech enhancement, noise reduction, echo cancellation, and beamforming.
- Improve multi-speaker handling with techniques such as VAD, source separation, and speaker diarization.
- Contribute to low-latency, multi-channel audio pipelines that can scale across thousands of drive-thru and phone channels.
AI & Speech Integration :
Work closely with ASR / LLM research and product teams to integrate DSP with automatic speech 1 recognition and conversational AI models.Collaborate on evaluation frameworks for speech quality, recognition accuracy, and latency—leveraging Langfuse-based observability.Engineering & Product Collaboration :
Partner with cross-functional teams (AI / ML, infrastructure, product, hardware) to make core architectural decisions.Prototype and evaluate new solutions—both software-based and hardware-assisted (microphones, speakers, sensors).Contribute to DTAI troubleshooting analytics by instrumenting DSP pipelines with rich observability hooks.Code & Process Quality :
Write clean, maintainable, and testable code.Actively participate in code reviews, debugging sessions, and system optimization.Drive engineering best practices in scalability, security, and future-proofing.Requirements
Must-Have
Bachelor’s or Master’s in Computer Science, Electrical Engineering, or related field.5+ years of professional experience in audio signal processing or speech technology.Strong experience with real-time audio processing systems (low latency, multi-channel).Deep understanding of VAD, beamforming, source separation, and speaker diarization.Hands-on experience with speech quality evaluation, ASR integration, and audio performance metrics.Proficiency in C++ / Python (or similar) for high-performance audio / DSP applications.Comfort working in a remote-first, distributed engineering team across multiple time zones.Nice-to-Have
Experience with AI / ML-based speech enhancement (deep learning noise suppression, end-to-end ASR frontends).Familiarity with observability frameworks for real-time systems (e.g., Langfuse, OpenTelemetry).Prototyping experience with hardware audio capture / playback devices.Exposure to restaurant / QSR operations or strong interest in consumer-facing speech applications.Working Terms
Must be flexible to work during US hours (until at least 6 p.m. ET).Must have own system / work setup for remote work.