• Took on a leadership role within the informatics team, acting as project manager during stand-up meetings, overseeing multiple projects to completion, and coordinating development efforts.

• Managed a Co-Op on a project to deploy and run machine learning models on AWS EC2 for molecular property prediction and clustering analysis.

• Built and maintained informatics data pipelines including developing infrastructure for training, evaluating, and using predictive machine learning models for ADMET data

• Developed tools for chemistry analysis, including data visualization and compound alignment tools using RDKit.

• Collaborated with internal developers and external consultants to maintain a robust CI/CD pipeline and ensure stable deployments.

• Continued performing previous duties, including: working with scientists to add new assay types into our database, ensuring fast and accurate data uploads across multiple projects (through automated data ingestion pipelines and manual uploads), gathering and acting on user feedback, and updating the informatics Django application.

• Managed a team of two engineers to successfully complete a software engineering project that developed a system for parsing internal patent documents. This system was used by the legal team to evaluate patent coverage.

• Built and optimized backend services using Python, Django, and PostgreSQL, improving query performance to ensure scalability as database size increased.

• Maintained a Dockerized deployment system, improving application maintainability and deployment efficiency.

• Implemented Celery for asynchronous task execution, enabling efficient large-scale data processing.

• Implemented Django REST Framework and an API client to automate compound inventory management system.

• Developed, tested, and deployed an internal drug discovery data management Django application used by chemists, biologists, and biochemists.

• Contributed to frontend development with JavaScript, enhancing user experience for scientific data visualization and streamlined user experience.

• Collaborated with cross-functional teams to design and implement scientific data querying tools.

• Updated and tested a tool to help biologists track and manage ongoing in vivo studies.

• Used Python Pandas library to develop a custom file parser for pharmacokinetics data.

• Implemented a programmatically generated assay templating system to standardize incoming data across multiple CROs.

• Wrote comprehensive documentation for the Informatics codebase, as well as for scientists using the tools the team was developing.

• Used MATLAB to overhaul data analysis protocol for a peer reviewed study, resulting in an efficient, intuitive, and accurate method used by lab technicians.

• Automated data processing protocols using macros in Excel VBA.

• Assisted physician during participant biopsies to acquire muscle tissue samples.

• Participated in professional development workshops and led formal presentations.