.OverviewAre you ready to drive PepsiCo's digital evolution and accelerate transformation across our global operations? As part of the Analytics stream of the Global Agro Digital Transformation initiative, this role will support the development of analytics use cases for Agro, mostly in data exploration and visualization, and modeling of agricultural processes (crop modeling, storage modeling). In this role, you will generate insights from agronomic data to provide recommendations to maximize agricultural production of supplies sustainably and with good quality.ResponsibilitiesYour day to day with us:Communicate with business stakeholders in the process of service design, training, and knowledge transfer.Day-to-day guidance of a small team of data scientists, aligning priorities and solutions with the project lead.Generate insights from agronomic data to provide recommendations to maximize agricultural production of supplies sustainably and with good quality.Ensure data access for discovery and proper data is prepared for model usage partnering with data engineers.Generate analytics pipelines and dashboards to refresh and share results for main use cases, including geo-spatial information, to enable stakeholders to access main results.Support large-scale experimentation and build data-driven models.Deploy reusable models and recommendations engines to different regions, with proper localization to its particularities.Research methodologies to fine-tune the approach for every analytics use case, with validation from leads.Generate reusable packages or libraries with proper documentation.QualificationsWhat you will need to succeed:1+ years of technical lead/coordination of a team of data scientists.2+ years client/stakeholder facing experience, to collect requirements/specifications, present results, and gather feedback.4+ years experience building solutions in revenue management or supply chain space.4+ years working in a team to deliver production-level analytic solutions - Fluent in git (version control).4+ years experience in ETL and/or data wrangling techniques - Fluent in SQL syntax.4+ years experience in Statistical/ML techniques to solve supervised (regression, classification) and unsupervised problems.3+ years experience in developing business problem-related statistical/ML modeling with industry tools with a primary focus on Python or PySpark development.Experience with MLOps framework design and building machine learning pipelines.Knowledge of containerization technology (Docker/Kubernetes) and REST API design.Additional qualifications that will make you stand out for this position:Ideally, experience with MLflow.What makes us different?Hybrid work model: combination of remote and collaborative office experience to enable innovation.Entrepreneurial environment in a leading international company.Professional growth possibilities & learning opportunities
