Efficient AI Researcher (Contract) – On-Device & Edge Models

LG Electronics; San Francisco (CA); Hybrid; USD 115,718 - 126,739; Part time

Benefits offered by this job

Health benefits

401(k) plan

Paid time off

Parental leave

Disability insurance

Job summary

LG Electronics is seeking a Contract AI Researcher focusing on Efficient AI in Santa Clara, CA, hybrid work arrangement. You will explore model compression, quantization, efficient inference, and architectures to make LLMs/VLMs faster and more deployable on devices.

You will bridge research and implementation, publish findings, and contribute to IP. Collaboration with experienced researchers and potential for project impact across LG products is expected.

Qualifications

• M.S./Ph.D. in CS or related field; relevant post-graduate research preferred.
• Experience in ML, efficient AI, model optimization, or AI systems.
• Proficient in Python and PyTorch; able to read research papers and run experiments.

Responsibilities

• Research, prototype, and implement AI methods that improve model efficiency, inference performance, and deployment on constrained devices.
• Optimize modern LLMs, SLMs, VLMs, and multimodal models across post-training, inference, and deployment workflows.
• Propose and evaluate compression methods (PTQ, QAT, pruning, low-rank) for on-device LLM/VLM enablement.
• Address long-context inference and KV cache compression in reasoning and agentic applications.
• Develop gradient-free and backpropagation-free methods for model merging and efficiency-driven optimization.
• Prototype inference-time optimization methods such as speculative decoding and low-latency generation.
• Build experimental pipelines, evaluate on language, vision, reasoning benchmarks.
• Contribute to publications, technical reports, and IP submissions where appropriate.

Skills

Python

PyTorch

LLMs

SLMs

VLMs

Multimodal models

ML research

Model optimization

Education

M.S./Ph.D. in CS

Tools

Llama.cpp

GGUF

vLLM

TensorRT-LLM

SGLang

Job description

LG Electronics is seeking a Contract AI Researcher focusing on Efficient AI in Santa Clara, CA, hybrid work arrangement. You will explore model compression, quantization, efficient inference, and architectures to make LLMs/VLMs faster and more deployable on devices.

You will bridge research and implementation, publish findings, and contribute to IP. Collaboration with experienced researchers and potential for project impact across LG products is expected.