Opportunity brief
About the Role
We're looking for an AI/ML Engineer with strong hands-on mobile app experience to help build and scale the intelligence layer behind Nuo — from voice-based stress detection to personalised recovery scheduling — directly within our Android (and eventually iOS) app. This is a high-ownership role for someone who can work across the ML pipeline and ship production mobile features, not just research in a notebook.
Responsibilities
- Design, train, and deploy ML models for voice-based stress/emotion detection, sleep-pattern inference, and calendar-gap analysis to personalise recovery recommendations. - Build and optimize on-device inference pipelines (e.g., TensorFlow Lite, ONNX Runtime, PyTorch Mobile) so voice processing happens on the spot and nothing is stored, in line with our privacy-by-architecture principles.
- Work closely with mobile engineers to integrate ML models into the Android app (Kotlin/Java) with a focus on low latency, low battery/resource impact, and background reliability.
- Develop the personalization logic behind the Recovery Score (0–100) — combining neuro reset
usage, voice stress trends, sleep, and calendar headroom into a single trajectory metric.
- Build and refine the recommendation/scheduling engine that decides which neuro sound reset to deliver, and when, based on real-time signals.
- Own the full ML lifecycle: data pipeline, feature engineering, model training/evaluation, deployment, monitoring, and iteration based on real user data.
- Collaborate with product and audio/science teams to translate neuroscience research
(Beta/Alpha/Theta wave protocols) into measurable, personalised ML-driven interventions.
- Ensure all ML processing respects strict privacy constraints — no raw audio storage, on-device or ephemeral processing wherever possible.
- Continuously monitor model performance in production and iterate based on user outcomes and feedback.