Edge AI Engineer: On-Device Models, Distillation & Quantization

Hyphen Connect; San Francisco (CA); On-site; USD 120,000 - 160,000; Full time

Job summary

Hyphen Connect seeks an AI Specialist Engineer in San Francisco to enhance AI performance on diverse hardware architectures. You will efficiently develop and deploy cutting-edge AI solutions. Responsibilities include compressing large models for on-device use, developing model distillation pipelines, and benchmarking across NPU/GPU architectures. Ideal candidates should have expertise in AI model optimization, strong C++ and Python skills, and hands-on experience with TensorRT and ONNX Runtime.

Qualifications

• Expertise in model distillation, pruning, and quantization techniques.
• Hands-on experience with TensorRT, ONNX Runtime, and edge deployment.
• Strong abilities in C++ and Python.

Responsibilities

• Compress and optimize large language and vision models for on-device inference.
• Develop pipelines for model distillation and hardware-specific compilation.
• Benchmark performance across NPU/GPU architectures.

Skills

Model distillation

C++

Python

TensorRT

ONNX Runtime

Job description

Hyphen Connect seeks an AI Specialist Engineer in San Francisco to enhance AI performance on diverse hardware architectures. You will efficiently develop and deploy cutting-edge AI solutions. Responsibilities include compressing large models for on-device use, developing model distillation pipelines, and benchmarking across NPU/GPU architectures. Ideal candidates should have expertise in AI model optimization, strong C++ and Python skills, and hands-on experience with TensorRT and ONNX Runtime.