Paolo Sandejas
About Paolo Sandejas
Paolo Sandejas is an AI Engineer with a background in data science and product management. He has contributed to various projects that enhanced machine learning models and strengthened partnerships with research institutions.
Work at Stratpoint Technologies
Paolo Sandejas is currently employed as an AI Engineer at Stratpoint Technologies, a position he has held since 2023. In this role, he has contributed to various projects that leverage artificial intelligence to enhance operational efficiency. His work has been instrumental in strengthening the company's partnerships, particularly with a prominent US research institute.
Previous Experience at Kodexa
Before joining Stratpoint Technologies, Paolo Sandejas worked at Kodexa in two capacities. He served as an Associate Product Manager from 2022 to 2023 for nine months, where he was involved in product development and management. Prior to that, he was a Data Science Intern for one month in 2021, gaining valuable experience in data analysis and machine learning.
Internships in Data Science and Technology
Paolo has a background in internships that provided him with practical experience in data science and technology. He interned at Wave Computing as a Data Science Engineering Intern in 2019 for one month. Additionally, he worked as an Information Technology Intern at Asia United Bank in 2021 for one month. These roles helped him develop essential skills in data processing and machine learning.
Education and Expertise
Paolo Sandejas studied at the University of the Philippines Diliman, where he earned a Bachelor of Science in Computer Science from 2018 to 2023. His academic background has equipped him with a solid foundation in computer science principles, programming, and data analysis, which he has applied in his professional roles.
Achievements in Machine Learning Projects
Throughout his career, Paolo has successfully developed machine learning pipelines that have demonstrated significant accuracy and efficiency. Notably, he enhanced a satellite imagery geolocation model, tripling its key evaluation metric within two months. He also developed machine learning pipelines that achieved over 90% accuracy in optimizing site selection for solar photovoltaic farms, addressing critical climate resiliency issues.