Software Engineer, Voice Interaction

Responsibilities

• Develop and maintain the full voice pipeline from microphone array input through wake word detection, STT, NLU, and TTS output
• Configure and integrate microphone arrays for domestic use, tuning beamforming, noise suppression, and echo cancellation
• Integrate the voice subsystem with high-level robot behaviors to enable intelligent action on voice commands
• Design and optimize TTS output for natural, real-time spoken interactions on embedded hardware
• Define and enforce guardrails around voice input and output, including content filtering and prompt boundary enforcement
• Evaluate and integrate STT/TTS engines, balancing accuracy, latency, and resource consumption
• Build reliable, well-tested software capable of running in real-world domestic environments with ambient noise and unreliable connectivity

Requirements

• 2+ years of experience developing voice-driven systems (STT, TTS, and real-time audio processing)
• Proficiency in C++, including experience with asynchronous programming and streaming/buffering patterns
• Experience working on compute-constrained platforms (robotics, edge devices, or consumer electronics)
• Strong understanding of both classical decision-making (state machines, behavior trees) and modern ML-driven reasoning (LLMs, VLMs)

Preferred Qualifications

• Experience as a founding or early hire in a startup environment
• Experience shipping responsive AI systems in robotics, video games, or embodied AI
• Strong understanding of ML-driven control for embodied AI, such as reinforcement learning or VLAs
• Practical experience interfacing with multimodal models
• Academic publications in multimodal models, audio interpretation, or robotics

About the Company

Sunday Robotics is developing personal robots designed to reclaim time lost to repetitive tasks. We are focused on making generalized robots broadly accessible to households, enabling people to take back quality time through innovative hardware and AI.