Android AI/ML Engineer (Enterprise & Security Innovation Lab) | Mountain View, CA - Onsite

Cohesive Technologies is a global IT Services & Solutions company providing IT Staffing Services and Application Development Services necessary for technology leaders to deliver business value. We help our people and clients succeed by leveraging our expertise, deep industry and market knowledge, proprietary assessment tools and techniques and project delivery methodologies. Through relationships with thousands of specialized professionals, we bring an unparalleled ability to match talent with opportunities by assessing, recruiting, developing and engaging the best and brightest people for our clients. We combine broad geographic presence, world-class solutions and a tailored, consultative approach to help our people and clients achieve higher performance and outstanding results.

Position Title: Android AI/ML Engineer (Enterprise & Security Innovation Lab)

Location: Mountain View, CA (On-site)

Duration: 6 months, with potential extension

Position Summary:

We are looking for an experienced Android AI/ML Engineer to develop advanced on-device machine learning systems that enable secure, adaptive, and scalable intelligence across mobile devices. The role emphasizes building intelligent, adaptive, and privacy-preserving ML systems that operate efficiently within the constraints of mobile environments. The ideal candidate will have strong experience in designing real-time, context-aware inference systems that can respond dynamically to local data patterns and behaviors.

Key Responsibilities:

• Design, develop, and deploy on-device machine learning models optimized for Android, ensuring low latency and minimal resource consumption.

• Build robust and scalable ML pipelines using Android-native frameworks such as:

  • TensorFlow Lite

  • ML Kit (including GenAI APIs)

  • MediaPipe

  • PyTorch Mobile

• Implement local signal aggregation and real-time pattern recognition logic to enable responsive in-app actions driven by on-device inference.

• Architect systems that support telemetry, secure logging, and privacy-first feedback collection for monitoring and evaluation.

• Apply model compression and optimization techniques (e.g., quantization, pruning, distillation) to meet mobile performance constraints.

• Develop secure, privacy-first solutions where all data processing and ML inference occur strictly on-device, with no external data exposure.

• Enable mechanisms for continuous local learning and model updates using device-resident data and signals, without compromising privacy.

• Ensure integration with Android's security model and collaborate with platform and product teams to deploy AI features safely at scale.

Technical Requirements:

• Proven experience in Android development (Kotlin/Java), with strong understanding of system architecture, resource management, and performance tuning.

• Hands-on expertise with on-device ML frameworks including TensorFlow Lite, ML Kit, MediaPipe, and PyTorch Mobile.

• Solid foundation in machine learning and signal processing techniques, such as time-series modeling, clustering, classification, and real-time event detection.

• Strong knowledge of mobile data handling and Android security practices, including permissions, sandboxing, and secure data storage.

• Understanding of privacy-preserving learning techniques and data governance in mobile environments.

• Familiarity with secure data handling on Android, including encrypted storage, permissions, sandboxing, and secure compute enclaves.

Experience with telemetry systems and evaluation pipelines for monitoring model performance on-device at scale.

Preferred Qualifications:

• Experience building ML-driven mobile applications in domains requiring user personalization, privacy, or security.

• Understanding of real-time data processing and behavioral modeling on resource-constrained edge devices.

• Knowledge of on-device learning techniques, federated learning, or personalization methods.

• Prior contributions to systems using federated learning, differential privacy, or local fine-tuning of models is a plus

• Experience with backend infrastructure for model management (e.g., model registries, update orchestration, logging frameworks) is a plus.

• Prior work with anomaly detection or behavioral modeling in resource-constrained environments is a plus.

• Experience developing responsive systems capable of monitoring local context and dynamically triggering actions based on model outputs is a plus

• Experience optimizing models for ARM architectures is a plus

• 5-7 years of experience with a Masters degree, 3+ years of experience with a PhD

Cohesive Technologies is an equal access/equal opportunity employer and does not discriminate on the basis of age, color, disability, marital status, national origin, race, religion, sex, sexual orientation, veteran status or any other classification prescribed by applicable law.