Agentic & Edge AI
Small Language Models on the Edge for Real-World Agentic Systems in Industry
SACAIR 2025
Combines small language models with agent workflows to run enterprise tasks locally.
In collaboration with
David Fernandez
PhD Candidate · Clemson University
AI Researcher · BMW Group
Research Assistant · U.S. Army’s Next Generation Combat Vehicle program
About Me
David Fernandez is a PhD candidate in Computer Science at Clemson University and an AI Researcher at BMW Group. His research focuses on safe, efficient, and explainable AI, spanning large language models, vision-language models, agentic systems, and adversarial robustness. His 10 papers include five first-authored studies on component-level explainability, zero-shot reasoning, and adversarial scenario analysis.
At BMW Group, he develops enterprise AI agents, automated prompt optimization, and defenses against multi-turn adversarial attacks. His work also includes edge AI for industrial agentic systems.
Through Clemson’s Virtual Prototyping of Ground Systems (VIPR-GS) program, he develops explainable reasoning and multimodal evaluation systems for the U.S. Army’s Next Generation Combat Vehicle program.
Education
- PhD in Computer Science , Clemson University (2024 – Present)
- MS in Data Science and Informatics , Clemson University (2022 – 2024)
- BS in Computer Engineering , ITAM, Mexico City
- BS in Business Administration , ITAM, Mexico City
Interests
- Explainable AI (XAI)
- Multimodal Foundation Model Architectures (LLMs & VLMs)
- AI Security and Adversarial Robustness in Autonomous Systems
- Agentic AI Systems and LLM Orchestration
- Autonomous Prompt Optimization and Meta-Learning
- Context-Aware AI Safety and Content Moderation
- Edge AI and On-Device Deployment
Research Highlights
VLM Security
Comparative Analysis of Patch Attack on VLM-Based Autonomous Driving Architectures
IEEE IV 2026
Benchmarks vision-language driving systems against physical attacks to uncover security weaknesses.
Research through
Explainable AI
From MIRAGE to CLEAR: Component-Level Explainable Anomaly Reasoning for Autonomous Vehicle Perception Systems
DSN 2026
Uses language models to identify which vehicle perception components failed and explain why.
Research at