AI Research Engineer · Multimodal AI (Audio + LLMs)
Building multimodal AI systems that combine audio and text. Research engineer specializing in explainability and production deployment. Completing PhD, available immediately.
Completing my PhD in Computer Science at University of Murcia with a thesis on "Enriched Feedback of Classroom Dynamics Using AI." 4+ years working with deep learning, mainly on combining audio and text data.
My work focuses on building AI systems that people can actually understand and use. I care about making systems explainable and deployable in production, rather than just chasing benchmarks.
Currently seeking: Research Engineer roles working on multimodal AI, explainability, or LLMs. Immediately available. Open to international opportunities.
Built a microservices system (Python, FastAPI, Docker, Celery) for analyzing classroom recordings using multimodal AI. Created audio processing pipelines combining speech recognition (Whisper), speaker identification, and text analysis (BERT). Used SHAP values to explain model predictions to make the system more transparent. Published a systematic review and 4 research papers on using AI in educational settings.
Provided technical support for enterprise clients using Google Cloud Platform. Troubleshot issues with Compute Engine, networking, IAM, and Kubernetes (GKE). Worked with SRE teams to debug production problems in cloud infrastructure.
Deployed a CNN model for real-time defect detection on embedded hardware (98% accuracy, <100ms latency). Built an LSTM model for evaluating text complexity. Managed ETL pipelines for various data types (tabular, image, audio) across R&D projects.
View my complete publication list on Google Scholar
PhD thesis on using multimodal AI to analyze classroom recordings and provide feedback to teachers, with a focus on explainability.
View Thesis →Combined text (BERT) and audio features to classify different types of teacher interventions in classrooms.
View Publication →Systematic review of 82 studies (2014-2024) on using audio processing in educational research.
View Publication →Explored techniques to make multimodal AI models generalize better across different classroom settings.
View Publication →Built a system to automatically analyze classroom recordings and generate insights for teachers.
View Publication →Analyzed how student response systems work in real classrooms using multimodal AI.
View Publication →Seeking Research Engineer roles in multimodal AI, explainability, or responsible AI development. Immediately available.