Eight years building production ML systems and distributed services in Python and Go model-serving platforms, real-time feature stores, and multi-agent AI workflows. Currently a PhD researcher at the JD-ICE European doctorate (UniGe · UC3M · QMUL) studying Vision-Language Models and hardware-aware inference.
Research on VLMs, Vision Transformers, and LLMs — hardware-aware inference for real-time edge deployments.
Multi-agent orchestration, tool-calling pipelines, RAG / GraphRAG on production serving infrastructure.
Model-serving platforms, real-time feature stores, and end-to-end MLOps pipelines at scale.
Event-driven microservices in Go and Python holding p99 latency stable through ~10× user growth.