Intelligent Edge Engineer - jobgether

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Intelligent Edge Engineer based in United States.

This role focuses on designing and deploying advanced AI solutions that operate directly on edge devices, bringing machine learning capabilities closer to users and real-world environments. You will develop and optimize models for mobile platforms, embedded systems, and specialized hardware while balancing performance, efficiency, and reliability. The position offers the opportunity to solve complex engineering challenges involving compute limitations, connectivity constraints, and hardware optimization. You will collaborate with multidisciplinary teams across engineering, product, and hardware domains to deliver impactful AI-powered experiences. The ideal candidate will contribute to the evolution of edge intelligence through innovative model optimization, secure deployment practices, and scalable architectures. This is a remote opportunity for an experienced engineer passionate about building production-ready AI systems beyond traditional cloud environments.

Accountabilities:

The Intelligent Edge Engineer will be responsible for creating efficient, secure, and scalable machine learning solutions optimized for deployment on resource-constrained devices. The role requires strong technical ownership across model optimization, edge architecture, performance engineering, and cross-functional collaboration.

• Design and deploy edge AI solutions optimized for mobile SoCs, NPUs, embedded accelerators, and specialized hardware platforms.
• Apply model compression techniques including quantization, pruning, and knowledge distillation to meet edge device requirements.
• Optimize machine learning models for latency, memory usage, power consumption, and overall performance.
• Build and maintain inference solutions using frameworks such as TensorFlow Lite, ONNX Runtime, and Core ML.
• Develop optimization strategies for accelerator backends including DSPs, NPUs, and mobile GPUs.
• Create reliable workflows for on-device model updates, version management, staged rollouts, and recovery processes.
• Design hybrid edge-cloud architectures that adapt to device capabilities and connectivity conditions.
• Build privacy-conscious telemetry systems that support continuous model improvement.
• Collaborate with hardware, firmware, product, and engineering teams to align AI solutions with technical constraints.
• Implement secure execution methods, model protection strategies, and integrity verification mechanisms.
• Develop benchmarking frameworks to evaluate accuracy, latency, energy efficiency, and device performance.
• Support responsible AI practices through privacy protection and bias evaluation.