Engineering & Technology Architect for R&D in Life Sciences and Biotechnology

Lead the design of scalable research informatics platforms that integrate complex experimental data across distributed laboratory environments. My work focuses on standardizing diverse scientific outputs into analysis‑ready data, improving reproducibility, data availability, and operational efficiency.  collaborate closely with scientists, engineers, and governance teams to delivered compliant, resilient solutions, define metadata standards, mitigate integration risks, and translate scientific needs into robust technical architectures.

I led the deployment of intelligent laboratory systems that enable closed‑loop monitoring, adaptive correction, and predictive maintenance in automated research environments. These efforts improved reliability, scalability, and experimental throughput. I also owned the evaluation and onboarding of external technologies, establishing standardized readiness frameworks and operating models that enabled compliant adoption of advanced automation solutions. In parallel, I supported broader lab modernization initiatives and assessed emerging technologies to inform future research operations.

I led the deployment of intelligent laboratory systems that enable closed‑loop monitoring, adaptive correction, and predictive maintenance in automated research environments. These efforts improved reliability, scalability, and experimental throughput. I also owned the evaluation and onboarding of external technologies, establishing standardized readiness frameworks and operating models that enabled compliant adoption of advanced automation solutions. In parallel, I supported broader lab modernization initiatives and assessed emerging technologies to inform future research operations.

Completed intensive technical onboarding at the global headquarters, focusing on enterprise automation standards and regulatory compliance protocols. Established foundational expertise in Eli Lilly’s proprietary system architectures to prepare for advanced, cross-site R&D deployments.

Advanced computational and embedded research systems for Miniature Mass spectrometry, focusing on performance and integration of hardware‑driven experiments with scalable engineering practices. Reduced computational overhead by ~55% by engineering optimized data‑processing models and introducing agile development workflows, CI/CD pipelines, and containerization—bringing production‑grade engineering discipline into an academic research environment. Integrated embedded hardware systems into computational research workflows, enabling advanced experimental studies through tight coupling of firmware‑level control with data acquisition and analysis pipelines. [Tools & Methods: Python, Docker, GitHub, CI/CD, Agile methodologies, STM32, Arduino, embedded systems, hardware–software integration]

Designed a data-driven computational system to detect blood–brain barrier (BBB) permeability from passive cavitation detection (PCD) signals acquired during focused ultrasound experiments.Architected a signal‑analysis pipeline, transforming high‑frequency acoustic emissions into time–frequency representations using Continuous Wavelet Transforms (Complex Morlet). Developed an unsupervised ML framework to identify experiment‑agnostic cavitation patterns, reducing reliance on brittle, frequency‑specific heuristics used in prior approaches. Achieved up to 90% accuracy in distinguishing BBB opening versus non‑opening events across heterogeneous datasets, validating results against experimental ground truth through quantitative statistical testing and establishing reproducible evaluation methodologies for future experimental and translational research. [Tools & Methods: Python, TensorFlow, time-frequency analysis]

Integrated real‑time Virtual and Augmented Reality environments with multi‑modal physiological biosensors to enable adaptive neurofeedback and behavioral simulations for neurological and mental health research. ·       Architected end‑to‑end real‑time biosignal analytics pipelines for multi‑modal physiological data (EEG, ECG, EMG, EOG, and EDA), enabling adaptive system behavior through continuous feedback loops and establishing early patterns for automation‑driven, resilient system design. Led the transition from research prototypes to scalable technology platforms through the co‑founding of a biomedical spin‑off, securing external funding, and directing an interdisciplinary team across system design, product development, and early operations. [Tools & Methods: Python, MATLAB, SQL/NoSQL].