Edge AI Research Engineer — Quantization & Inference

Insider, Inc.; United States; On-site; USD 100,000 - 150,000; Full time

Job summary

Insider, Inc. is seeking an experienced AI Research Engineer to optimize deep learning models for edge AI platforms. This role involves research on quantization techniques, implementing low-bit precision optimizations, and collaborating with hardware engineers. The ideal candidate has a Master’s or Ph.D. in Computer Science or Electrical Engineering, and is proficient in Python and C++. Familiarity with frameworks like PyTorch and TensorFlow is essential. The position offers a unique opportunity to enhance AI model performance in critical applications.

Qualifications

• Strong expertise in deep learning and numerical precision analysis.
• Hands-on experience with model quantization techniques (QAT, PTQ).
• Familiarity with compiler optimizations for ML workloads.

Responsibilities

• Research and develop quantization-aware training and post-training quantization techniques.
• Implement low-bit precision optimizations such as INT8 and BF16.
• Collaborate with hardware engineers to optimize model execution for edge devices.

Skills

Deep learning

Model optimization

Quantization techniques

Python

C++

Education

Master’s or Ph.D. in Computer Science or Electrical Engineering

Tools

PyTorch

ONNX Runtime

TVM

TensorFlow

Job description

Insider, Inc. is seeking an experienced AI Research Engineer to optimize deep learning models for edge AI platforms. This role involves research on quantization techniques, implementing low-bit precision optimizations, and collaborating with hardware engineers. The ideal candidate has a Master’s or Ph.D. in Computer Science or Electrical Engineering, and is proficient in Python and C++. Familiarity with frameworks like PyTorch and TensorFlow is essential. The position offers a unique opportunity to enhance AI model performance in critical applications.