San Francisco Bay Area
We're hiring an AI Audio / Voice Engineer to build the audio front door to Nirva's intelligence layer: systems that capture only the wearer, reliably, privately, and with as much processing on device as possible.
Nirva is building the first AI fashion accessory for your mind — a necklace or bracelet that privately listens only to the wearer to enable proactive journaling, emotion tracking, and life coaching. Think Oura Ring for your Mind.
Backed by Lightspeed and South Park Commons, recognized at CES within 90 days of founding, and launching in the U.S. this fall. Co-founders bring backgrounds from Meta Reality Labs (Quest, Ray-Ban glasses) and fashion industry.
This is the trust foundation for the whole product.
Build voice systems that recognize the wearer, exclude bystanders, and balance privacy, reliability, and on-device performance.
Voiceprint enrollment, voice embeddings, verification, and identification so Nirva recognizes the wearer and separates them from bystanders, family, coworkers, and media.
Tune and evaluate voiceprint in the real world, including false accepts, false rejects, noisy environments, voice drift, and re-enrollment.
Anti-spoofing and trust protections, including replay and impersonation resistance.
Build the on-device audio pipeline: voice activity detection, segmentation, speaker filtering, audio preprocessing, noise suppression, and streaming to speech recognition within tight latency, power, thermal, and memory budgets.
Decide the on-device versus cloud split and build fallbacks.
Build trust by design through on-device first processing, bystander exclusion, consent and recording controls, encryption, data minimization, and retention and deletion controls.
2+ years of full-time engineering experience, or a PhD in computer science, electrical engineering, machine learning, speech or audio, or a related field, plus 2 applied internships where you shipped or evaluated real systems.
Deep, hands-on knowledge of at least one of these and working knowledge of the other two: voiceprint or speaker verification and identification, on-device audio ML, and trust, privacy, and security for audio sensing.
Experience with speech and audio ML in production, including speaker embeddings, diarization, VAD, streaming audio, speech-to-text, and audio preprocessing.
Experience with on-device or edge ML, including quantization, distillation, latency optimization, and power optimization.
Strong evaluation mindset for audio systems.
Nice to have experience with always-on or low-power audio, wearables, hearables, mobile audio, iOS audio, Core ML, embedded or DSP, or privacy engineering.
Location: San Francisco Bay Area, in person.
Type: Full-time.
Pay: $180k–$350k, level dependent, plus meaningful equity.