Software Engineer, Robot Interfaces

What You’ll Do Develop and maintain the full voice pipeline from microphone array input through wake word detection, speech-to-text, natural language understanding, and text-to-speech output Configure and integrate microphone array for domestic use, tuning onboard audio processing (beamforming, noise suppression, echo cancellation) and supplementing with additional processing where needed Integrate the voice subsystem with high level robot behaviors, enabling the robot to receive, interpret, and act intelligently on voice commands Design and optimize TTS output to deliver natural, responsive spoken interactions in real time on embedded hardware Define and enforce guardrails around voice input and output, including content filtering, prompt boundary enforcement, output length limits, and auditing to ensure the system operates within intended use Evaluate and integrate STT/TTS engines and models, making informed tradeoffs between accuracy, latency, and resource consumption Build reliable, well-tested software that runs on our robot, Memo, under real-world conditions including ambient noise, partial utterances, and unreliable network connectivity Deliver a successful voice interaction experience to our Beta users What You’ll Bring 2+ years experience developing voice-driven systems including speech-to-text, text-to-speech, and real-time audio processing, with at least one end-to-end pipeline shipped to users or deployed on hardware Strong understanding of both classical decision-making approaches (state machines, behavior trees, planning) and modern ML-driven reasoning (LLMs, VLMs) Experience working on compute-constrained platforms where software meets hardware (robotics, edge devices, consumer electronics, or similar) including debugging problems that cut across both Proficiency in C++, with experience in asynchronous programming, streaming/buffering patterns, and integration with cloud API services Nice To Have Experience as a founding or early hire; able to define a release roadmap where no blueprint exists Experience shipping responsive AI systems in robotics, video games, or embodied AI Strong understanding of ML-driven control for embodied AI (end-to-end learning, reinforcement learning, VLAs) Practical experience (or high curiosity) in interfacing with multimodal models Publications in multimodal models, audio interpretation, or robotics At Sunday Robotics, we’re building technology shaped by real people — curious, creative, and diverse. We’re proud to be an equal opportunity employer and consider all qualified applicants regardless of race, color, religion, gender, gender identity or expression, sexual orientation, national origin, genetics, disability, age, or veteran status. #J-18808-Ljbffr