Efficient AI Researcher - On-Device Models & Edge AI

LG Electronics USA; Santa Clara (CA); Hybrid; USD 120,000 - 180,000; Full time

Job summary

LG Electronics USA's Emerging Technology Lab in Santa Clara, CA seeks a Contract AI Researcher focused on Efficient AI. You will explore model compression, quantization, and on-device inference to make LLMs and multimodal models faster and lighter for real-world applications.

The role blends research with hands-on implementation, collaborating with researchers to publish findings, contribute to IP, and drive measurable improvements across LG's future products, including AI PCs, edge devices, and

Qualifications

• MS/PhD in Computer Science, Engineering, Mathematics or related field.
• Experience in ML, efficient AI, model optimization, or AI systems.
• Strong Python and PyTorch experience; ability to read and implement research papers.

Responsibilities

• Research methods to improve model efficiency and deployment on constrained devices.
• Optimize LLMs/SLMs/VLMs and multimodal workloads across post-training and inference.
• Propose compression methods (PTQ, QAT, pruning) for on-device AI.
• Prototype inference-time optimization and kernel-level enhancements.
• Contribute to publications, IP disclosures, and open-source efforts.

Skills

Python

PyTorch

ML Research

Model Optimization

On-device AI

Prototyping

Education

MS/PhD in CS/ML

Tools

llama.cpp

GGUF

vLLM

TensorRT-LLM

CUDA

Job description

LG Electronics USA's Emerging Technology Lab in Santa Clara, CA seeks a Contract AI Researcher focused on Efficient AI. You will explore model compression, quantization, and on-device inference to make LLMs and multimodal models faster and lighter for real-world applications.

The role blends research with hands-on implementation, collaborating with researchers to publish findings, contribute to IP, and drive measurable improvements across LG's future products, including AI PCs, edge devices, and