Vibotek LLC
Android AI/ML Engineer - Infrastructure (AI ML Ops Engineer III)
Job Category:
Technical
Position Summary We seek an experienced Android AI/ML Engineer to design and deploy on-device machine learning systems for mobile devices. This role focuses on creating efficient, adaptive, and privacy-preserving ML systems that perform in real-time within mobile constraints.
Key Responsibilities
Develop, optimize, and deploy on-device ML models for Android with minimal latency and resource consumption.
Build ML pipelines using Android-native frameworks (TensorFlow Lite, ML Kit, MediaPipe, PyTorch Mobile).
Implement real-time pattern recognition and signal aggregation to drive in-app responses.
Design systems for telemetry, secure logging, and privacy‑first feedback collection.
Apply model optimization techniques (e.g., quantization, pruning) to meet mobile performance constraints.
Enable local, privacy-preserving learning and model updates on-device.
Integrate solutions with Android's security model, ensuring safe deployment at scale.
Required Skills
Strong experience in Android development (Kotlin/Java) and system architecture.
Expertise in on-device ML frameworks like TensorFlow Lite, ML Kit, MediaPipe, PyTorch Mobile.
Solid understanding of machine learning, signal processing (time‑series modeling, classification, event detection).
Knowledge of Android security practices (permissions, encryption, sandboxing).
Experience with telemetry systems and performance monitoring.
Preferred Qualifications
Experience in user personalization, privacy, or security domains.
Knowledge of on-device learning, federated learning, or local model fine‑tuning.
Experience with backend infrastructure for model management.
Familiarity with ARM architectures and model optimization.
Education and Experience
5–7 years of experience with a Master’s degree or 3+ years with a PhD.
Seniority Level Mid‑Senior level
Employment Type Full‑time
Job Function Engineering and Information Technology
#J-18808-Ljbffr
Job Category:
Technical
Position Summary We seek an experienced Android AI/ML Engineer to design and deploy on-device machine learning systems for mobile devices. This role focuses on creating efficient, adaptive, and privacy-preserving ML systems that perform in real-time within mobile constraints.
Key Responsibilities
Develop, optimize, and deploy on-device ML models for Android with minimal latency and resource consumption.
Build ML pipelines using Android-native frameworks (TensorFlow Lite, ML Kit, MediaPipe, PyTorch Mobile).
Implement real-time pattern recognition and signal aggregation to drive in-app responses.
Design systems for telemetry, secure logging, and privacy‑first feedback collection.
Apply model optimization techniques (e.g., quantization, pruning) to meet mobile performance constraints.
Enable local, privacy-preserving learning and model updates on-device.
Integrate solutions with Android's security model, ensuring safe deployment at scale.
Required Skills
Strong experience in Android development (Kotlin/Java) and system architecture.
Expertise in on-device ML frameworks like TensorFlow Lite, ML Kit, MediaPipe, PyTorch Mobile.
Solid understanding of machine learning, signal processing (time‑series modeling, classification, event detection).
Knowledge of Android security practices (permissions, encryption, sandboxing).
Experience with telemetry systems and performance monitoring.
Preferred Qualifications
Experience in user personalization, privacy, or security domains.
Knowledge of on-device learning, federated learning, or local model fine‑tuning.
Experience with backend infrastructure for model management.
Familiarity with ARM architectures and model optimization.
Education and Experience
5–7 years of experience with a Master’s degree or 3+ years with a PhD.
Seniority Level Mid‑Senior level
Employment Type Full‑time
Job Function Engineering and Information Technology
#J-18808-Ljbffr