Job Description
📋 Description Real-time on-device speech translation app running on iPhone Implement audio capture → speech recognition → translation → text-to-speech pipeline Integrate on-device ML models and manage OTA model delivery from AWS Build peer-to-peer device communication and production delivery through a federal accreditation Maintain performance, memory management, and reliability on constrained devices Collaborate across services and modules in a security/compliance environment 🎯 Requirements 5+ years shipping production iOS apps in Swift Direct experience with AVAudioEngine or AudioUnit at hardware callback level Experience with ML or signal-processing frameworks (Core ML, ONNX, TensorFlow Lite, or similar) Proficiency with memory and performance tuning on constrained devices (Instruments) Experience with background URLSession and resilient download/upload systems Comfort with protocol-oriented architecture, multi-module Swift packages, and testable service 🎁 Benefits Competitive compensation and federal-compliance oriented environment Generous and flexible time-off policy Flexible work schedules and remote options for eligible projects Industry-leading benefits including health, dental, vision, FSA, commuter benefits, life insurance 401K with matching Career development and mentorship opportunities
