About the role
Join Optasia, a pioneering B2B2X financial technology platform committed to revolutionizing financial inclusion through innovative solutions in scoring, financial decision-making, disbursement, and collection. We are dedicated to changing the world with our unique approach.
We are looking for passionate professionals who embody energy, a results-oriented mindset, and a proactive attitude. If you're eager to collaborate with a team of like-minded individuals in a dynamic environment, this is the perfect opportunity for you.
At Optasia, data is central to our growth strategy, and our Machine Learning Engineering team plays a crucial role in driving our success through data-driven insights and decision-making. We are currently harnessing data from diverse sources into our extensive big data clusters and developing and managing multiple analytical pipelines using cutting-edge technology.
As an ML Infrastructure Engineer, you will be integral to our data-driven automated decision-making and risk management processes. Your expertise in machine learning flows and the development and deployment of advanced algorithms will be invaluable. Key responsibilities include:
- Designing and developing microservices and tools to support the Machine Learning lifecycle at Optasia.
- Creating scalable, real-time microservices for global use.
- Enhancing the development lifecycle through continuous improvements in collaboration with the team.
- Designing, developing, and maintaining large-scale Spark jobs utilizing PySpark and Scala.
- Building and managing CI/CD pipelines through Jenkins.
- Writing automation scripts in Python or Bash.
- Creating and deploying scalable Airflow pipelines that facilitate the Machine Learning lifecycle.
- Conducting data exploration and analysis to develop and iterate on Machine Learning proof-of-concepts (PoCs).
- Collaborating with Engineers and the Credit Risk team to design and deliver solutions that provide significant business value.
- Optimizing the codebase through Spark job tuning and refactoring.
- Improving our feature engineering engine to support more efficient Machine Learning workflows.

