About
I hold a PhD in Computer Science and Artificial Intelligence from the University of Murcia, awarded with Summa Cum Laude honors. Over the past 4+ years, my work has centered on bridging the gap between cutting-edge AI systems and robust, production-ready software engineering.
My expertise focuses on developing multimodal architectures (combining audio processing with Large Language Models), orchestrating scalable data pipelines, and implementing Explainable AI (XAI) frameworks. I prioritize building reliable, high-availability microservices over simply chasing theoretical benchmarks.
Experience
AI Engineer
Designed and deployed a decoupled microservices architecture (Python, FastAPI, Docker, Celery) for multimodal AI inference, optimizing processing latency across local and cloud infrastructure. Built end-to-end audio processing pipelines integrating ASR (Whisper), speaker diarization, paralinguistic feature extraction, and semantic vector embeddings (FAISS). Applied Explainable AI (XAI) frameworks utilizing SHAP values to interpret fine-tuned BERT models, delivering complete system transparency. Published 5 high-impact, first-author research papers in venues like IEEE Access and Applied Sciences.
Data Scientist & Machine Learning Engineer
Deployed an industrial real-time CNN for automated defect detection, achieving 98% accuracy and sub-100ms inference latency running directly on resource-constrained embedded hardware. Developed optimized LSTM-based NLP systems for semantic complexity analysis. Built and maintained automated, multi-source ETL pipelines for tabular, image, and raw audio data assets.