Contact Us
Talk to us about kernel-level optimization, Nova Engine, or Agentic Commerce pilots.
Email Us
Visit Us
LLM Core AI HQ
SNU Bldg #34: College Of Engineering Bldg #5
Naval and Ocean Architecture Engineering
1 Gwanak-ro, Gwanak-gu, Seoul
Send us a message
Frequently Asked Questions
Q.What do you optimize?
Inference performance end-to-end: kernels (e.g., GEMM/attention), scheduling, batching, and serving bottlenecks—focused on measurable throughput/latency gains.
Q.Is Nova Engine hardware-specific?
No. Nova Engine is designed to be hardware-agnostic, maximizing performance across modern GPU/SoC systems.
Q.How do I start a pilot?
Choose “Partnership” in the form and share your target workflow and constraints. We’ll propose scope, milestones, and success metrics.