Senior iOS Engineer (CoreML / Real-Time Audio)

About the Product

We are building an iOS application with real-time on-device audio processing powered by CoreML.

All ML logic runs fully on-device.
No raw audio is stored or sent to the backend.

We are looking for an engineer who has already built real-time audio + ML features in production and can start delivering immediately — no onboarding, no learning curve.

You MUST Have

• Proven commercial experience with CoreML in production
• Experience building real-time audio pipelines
• Hands-on work with AVAudioEngine
• Experience integrating audio streams into ML models
• Experience running audio + ML in background mode
• Performance optimization on real devices

If you do not have production experience with CoreML and real-time audio — this role is not a fit.

Responsibilities

• Build and maintain the pipeline:
  Microphone → Audio processing → Feature extraction → CoreML inference → UI
• Optimize latency and CPU usage
• Ensure stability across devices
• Handle background audio execution
• Maintain strict privacy (no raw audio storage)

Nice to Have (but still relevant)

• Experience with Accelerate / vDSP
• Experience with SoundAnalysis
• Experience with acoustic event detection (laughter, shouting, silence, etc.)

One-Line Summary of Who We’re Looking For

A production-ready Senior iOS engineer who has already shipped real-time CoreML audio features and can work independently from day one.