education

2019 - Present

• Machine Learning & Deep Learning Expertise: Gained advanced knowledge in developing and deploying machine learning and deep learning models. Specialized in techniques such as LSTMs for regression and forecasting, as well as deep generative models for molecular property prediction, addressing challenges in solubility and potency estimation.
• Software Engineering Leadership: Developed the ability to lead software development teams, emphasizing collaboration, code quality, and agile methodologies. Gained experience in driving end-to-end software lifecycle processes, from design to deployment.
• Algorithms & Optimization: Strengthened skills in algorithm design and optimization using C, C++, and Python, focusing on creating efficient and scalable solutions for computationally intensive problems.
• Web Development Mastery: Acquired expertise in developing responsive, user-centric web applications using modern frameworks like React and Angular, leveraging both JavaScript and TypeScript to build high-performance interfaces.
• Distributed Systems & Cloud Architecture: Learned the principles of designing and deploying distributed systems, emphasizing scalability, fault tolerance, and performance. Built secure, cloud-native solutions on platforms like AWS and GCP.
• Backend Systems Development: Mastered API and database design, developing RESTful APIs using NodeJS and Java while managing relational and NoSQL databases such as MySQL and MongoDB.
• Problem-Solving & Systems Thinking: Cultivated a deep understanding of complex systems design, enabling the implementation of innovative solutions to address multifaceted technical challenges across machine learning, web development, and cloud environments.

August 2015 - May 2017

• Molecular Modeling: Developed and applied advanced molecular dynamics (MD) simulations to study chemical properties, leveraging tools like CHARMM and OPLS to analyze the interactions and stability of quaternary ammonium compounds.
• Small Molecule Property Prediction: Focused on predicting molecular properties critical to pharmaceutical and chemical industries, including potency and solubility, utilizing computational chemistry techniques and machine learning models.
• Machine Learning for Molecular Prediction: Built and deployed machine learning models using Python, Keras, and RDKit to predict chemical properties, automate ligand classification, and enable ligand clustering for enhanced compound categorization.
• Deep Learning Applications in Structural Biology: Applied deep learning techniques to predict molecular structures and analyze ligand-receptor interactions, providing insights into binding mechanisms and structure-activity relationships.
• Quantitative Structure-Activity Relationship (QSAR) Analysis: Conducted QSAR studies using graph theory and machine learning algorithms, establishing correlations between chemical structures and biological activity to guide compound design.
• Database Development & Data Management: Designed and managed relational databases using MySQL and SQLite3 to organize, store, and retrieve complex molecular datasets, facilitating efficient data analysis and retrieval.
• Cross-Disciplinary Collaboration: Bridged life sciences and computational sciences by integrating molecular modeling with data science approaches, enabling a holistic understanding of chemical and biological systems.
• Potency Prediction through MD Simulations: Developed MD-based simulation models using Python and JavaScript to predict ligand potency, streamlining the drug discovery process by providing accurate and reproducible computational predictions.

September 2011 - May 2015

• Molecular Dynamics & Protein Simulation: Gained foundational expertise in utilizing CHARMM and OPLS force fields for protein simulation development, enabling detailed insights into protein structures and dynamics.
• Computational Analysis of Proteins: Conducted protein analysis using industry-standard tools like Schrödinger and MOE, focusing on structural predictions and functional insights to advance understanding of protein behavior.
• Machine Learning in Ligand Clustering: Applied supervised machine learning techniques to classify and cluster ligands, exploring structure-activity relationships and facilitating data-driven decision-making in molecular design.
• Python for Scientific Computing: Developed and optimized Python2 and Python3 scripts for automated molecular dynamics (MD) analysis, streamlining workflows and improving computational efficiency.
• Chemical Analysis: Conducted advanced chemical analyses of inks, pigments, and resins using liquid chromatography-mass spectrometry (LC-MS) and microwave-assisted reaction systems (CEM MARS6), contributing to material characterization and quality control.
• Data-Driven Insights in Computational Chemistry: Leveraged computational tools and algorithms to bridge theoretical chemistry with practical applications, building a strong foundation in molecular modeling and data analysis.
• Integration of Chemistry and Computation: Combined principles of chemistry, computer science, and data science to solve complex chemical challenges, laying the groundwork for advanced studies in computational chemistry and molecular modeling.