Abolfazl Afkhami

Python, PyTorch, Hugging Face, Whisper, RAG, n8n, Docker, Linux, OpenCV, FastAPIs, Gemini API

Low-latency streaming ASR architectures, advanced LLM inference optimization, and distributed agentic evaluation frameworks.

Fine-tuning Whisper for low-resource ASR and building dynamic-sync RAG pipelines with sub-second latency.

Contract engineering, Speech AI/ASR pipelines, production RAG systems, and AI agent workflow architecture for global teams.