ChengRung Wu (Roger)
About
Software engineer with 9 years building and deploying mission-critical systems in the national-security sector — progressing from engineer to technical lead. Now focused on self-hosted / air-gapped LLM infrastructure and low-resource speech AI. M.S. in Computer Science from NYCU; AWS Solutions Architect. Open to opportunities in 2027.
Experience
Lead technical direction for AI-infrastructure and large-scale data-processing initiatives; architect self-hosted, fully-offline LLM and speech-processing platforms; mentor engineers.
Designed and deployed a large-scale signal & geospatial data-processing platform, cutting analysis turnaround 60%; built a speaker-recognition / speech-to-text pipeline (−50% manual workload).
Built a network-planning & resource-optimization web application; delivered a virtualized data-processing system (+70% efficiency); scaled the engineering team from 1 to 10+.
Featured Projects
Enterprise Air-Gapped LLM Platform
Production self-hosted LLM platform for air-gapped, security-critical environments. 30B MoE model across dual GPUs via tensor parallelism, fully offline, AD/LDAPS auth.
YaYan-AI — Speech Intelligence
Fully-offline multi-dialect speech-to-text & translation: 22 Chinese dialects + 40 languages, 5-speaker diarization, LLM-assisted correction.
OpenClaw Agents
Framework of autonomous LLM agents — OODA-loop decision support and news-intelligence briefing — with persona-driven design and credential-isolated deployment.
yolov5-parallel
Parallelized YOLOv5 training and inference pipeline for multi-GPU throughput.