Computational Biological Engineer focused on deep learning applications in in-silico experimentation and therapeutic reasoning for personalized medicine. Develops AI-driven agents that simulate therapeutic interventions based on individual patient phenotypes and molecular profiles, enabling real-time, patient-specific modeling to support clinical decision-making. Research centers on designing systems that replace generalized treatment assumptions with adaptive, evidence-grounded simulations. The work integrates pharmacological, genetic, and clinical data, employing structured RDF/OWL ontologies, formal knowledge graphs, and biomedical toolchains. Key contributions include: 1) Construction of a biomedical reasoning agent trained on >150,000 clinical reasoning traces and >250,000 structured tool calls. 2) Development of a modular architecture incorporating retrieval-augmented generation, ontology-grounded querying, and dynamic tool assembly. 3) Benchmarking of model performance across 3,000+ therapeutic tasks, achieving ~90% accuracy and outperforming baseline LLMs by 25–50%. The system is capable of simulating treatment efficacy, predicting adverse effects, resolving drug nomenclature ambiguities, and supporting drug repurposing for complex diseases. Outputs include complete reasoning traces for traceability and compliance. Current efforts emphasize continual adaptation to new biomedical APIs, datasets, and regulatory guidelines. Research interests: in-silico experimentation, therapeutic reasoning, biomedical ontologies, deep learning, RDF knowledge graphs, clinical decision support systems, personalized medicine, AI in healthcare.