Data Scientist

Responsibilities

• Maintain and enhance the existing optimization model by proactively identifying shortcomings and implementing improvements.
• Present model outputs and analytical findings to stakeholders, gather and translate business requirements into technical solutions, and maintain clear, consistent communication with all stakeholders throughout the project lifecycle.
• Ensure the robustness and efficiency of the deployed AI product on GCP through continuous monitoring and maintenance.
• Improve the data preparation and wrangling pipeline, and integrate additional data sources to enrich model inputs.
• Collaborate with Data Scientists, ML Engineers, and Product Managers to improve the performance, reliability, and scalability of the optimization model.
• Implement MLOps best practices for seamless deployment, monitoring, and lifecycle management of machine learning models.
• Conduct ad hoc data analyses and develop visualizations to support data driven decision making across teams.

Required Skills

• Solid knowledge and experience in discrete optimization models (Integer Programming, Mixed Integer Programming).
• Proven experience developing and deploying ML models in the cloud, preferably on GCP (beyond notebook-based coding and execution).
• Solid Python programming skills—writing clean, efficient, modular, and production-ready code that is easy to maintain and test.
• Hands-on experience with MLOps and CI/CD pipelines, ideally on GCP. Strong SQL skills for data manipulation and analysis.
• Ability to understand diverse data sources and build robust data wrangling and aggregation pipelines. Familiarity with DBT for data transformation.
• Comfortable working in Agile, cross-functional teams.
• Strong collaboration skills and ability to thrive in complex, ambiguous problem domains.