Remote Edge AI Engineer — On-Device ML & Optimization

Bright Vision Technologies; United States; Remote; USD 100,000 - 155,000; Full time

Job summary

Bright Vision Technologies is seeking an experienced Edge AI Engineer to design, optimize, and deploy ML models for edge devices across mobile, embedded, and accelerators. You will work on quantization, compression, and hardware-aware optimization to deliver production-ready AI at the edge.

This 100% remote, full-time role requires 8+ years of ML experience and strong Python/C++ skills. You will collaborate with hardware, firmware, and product teams to ship reliable AI capabilities with

Qualifications

• Eight+ years of ML engineering experience, with edge/mobile focus.
• Strong Python and C++ proficiency.
• Experience with model compression and quantization.
• Production deployment on mobile/embedded platforms.
• Familiarity with on-device privacy and security.
• Experience with at least one major edge inference framework.

Responsibilities

• Design edge AI solutions optimized for diverse hardware (mobile SoCs, NPUs, embedded accelerators).
• Apply quantization, pruning, distillation, and architectural optimization for edge constraints.
• Tune performance for latency, energy, and memory on target hardware.
• Build cross-platform inference runtimes using TensorFlow Lite, ONNX Runtime, Core ML.
• Optimize models for accelerator backends (DSPs, NPUs, mobile GPUs).
• Implement on-device model update, versioning, and rollback workflows for safe staged rollouts.

Skills

Python

C++

ML on edge/mobile

Model compression

Profiling

Education

Bachelor’s or Master’s degree in CS/CE

Tools

TensorFlow Lite

ONNX Runtime

Core ML

Edge inference frameworks

Job description

Bright Vision Technologies is seeking an experienced Edge AI Engineer to design, optimize, and deploy ML models for edge devices across mobile, embedded, and accelerators. You will work on quantization, compression, and hardware-aware optimization to deliver production-ready AI at the edge.

This 100% remote, full-time role requires 8+ years of ML experience and strong Python/C++ skills. You will collaborate with hardware, firmware, and product teams to ship reliable AI capabilities with