AI Researcher (Efficient AI)

The role

You will research, prototype, and implement AI methods to improve model efficiency, inference performance, and deployment on constrained devices. This work involves optimizing LLMs, VLMs, and multimodal models for products like AI PCs, edge devices, robotics, and intelligent vehicle systems.

What you will do

• Research, prototype, and implement AI methods that improve model efficiency, inference performance, and deployment feasibility on constrained devices.
• Optimize modern LLMs, SLMs, VLMs, multimodal models, and agentic workloads across post-training, inference, and deployment workflows.
• Propose and evaluate novel compression methods for on-device LLM/VLM enablement.
• Devise approaches to address challenges related to long-context inference and KV cache compression.
• Develop gradient-free and backpropagation-free methods for model merging, compression, and efficiency-driven optimization.
• Implement and evaluate emerging efficient architectures and modules.
• Prototype inference-time optimization methods such as speculative decoding, constrained decoding, low-latency generation, and kernel-level optimization.
• Build experimental pipelines and perform evaluations on standardized benchmarks.
• Contribute to publications, technical reports, open-source releases, invention disclosures, and IP submissions.

Required qualifications

• M.S. or Ph.D. in Computer Science, Computer Engineering, Machine Learning, Mathematics, or a related technical field.
• Research or engineering experience in ML, efficient AI, model optimization, or AI systems.
• Strong programming ability in Python and experience with PyTorch or a comparable deep learning framework.
• Hands-on experience with modern LLMs, SLMs, VLMs, multimodal models, or generative AI systems.
• Ability to read research papers, implement technical methods, run experiments, and communicate results clearly.
• Comfortable working in a fast-moving and ambiguous technical environment.
• Strong written and verbal communication skills for reports, presentations, demos, and technical documentation.

Nice to have

• Publications in reputable venues in ML and/or systems space (e.g., ICML, ICLR, NeurIPS, ACL, COLM, EMNLP, MLSys, MICRO, etc).
• Experience with modern LLM/VLM inference and deployment frameworks such as llama.cpp, GGUF, vLLM, SGLang, TensorRT-LLM, or related systems.
• Experience with efficiency-aware post-training or finetuning methods such as PTQ, QAT, LoRA, distillation, instruction tuning, DPO, OPD, RLVR, or reasoning-oriented adaptation.
• Experience with low-level kernel implementations and on-device acceleration.
• Familiarity with emerging architectures such as MoE, SSMs, hybrid attention, or Looped Transformers.
• Experience with AI-assisted optimization, multi-agent systems, or agentic-based workflows for Efficient AI and hardware/software co-design.
• Relevant post-graduate research and/or industry experience

Benefits

• Eligible for the relevant benefit programs offered through our partner agencies.

Before you apply

• We are not accepting unsolicited resumes or candidate submission from staffing agencies or search firms for this position.

About the company

LG Electronics is a global leader in technology with a diverse portfolio including Home Appliance Solutions, Media Entertainment Solutions, Vehicle Solutions, and Eco Solutions. LG's Emerging Technology Lab (ETL) is the catalyst for technological innovation within LG’s CTO organization.