AI Engineer for Production LLM Systems and Inference
Philippines
Anglais
Certaines informations sont présentées en anglais.
À propos de moi
AI engineer focused on transformer internals and inference systems. I build production self-hosted LLM systems for teams that need real understanding of what's happening under the hood, not just API integration.
Specialties: vLLM and Ollama serving with quantization for limited VRAM, RAG pipelines with measured retrieval quality, faster-whisper transcription, fine-tuning and evaluation, activation analysis, Proxmox VFIO GPU passthrough, custom FastAPI services.
Working style: written spec first, fixed price with milestones, real benchmarks before quoting numbers.... Plus d’infos