ML Engineer (Forecasting & Applied Data Science)

As an ML Engineer specializing in forecasting and applied data science, you’ll design, deploy and maintain predictive models at scale for a US tax technology company.

You’ll turn commercial problems in demand, pricing and customer behavior into production-ready machine learning solutions. As a senior member of the team, you’ll own end-to-end ML pipelines, work closely with business teams, and mentor other data professionals. 100% remote from Latin America, full-time contracting.

What you’ll do

• Design, build and maintain production-scale forecasting and time series models for demand and other key business metrics.
• Build and optimize data pipelines that keep production models reliable, traceable and fed with quality data.
• Work with marketing, retail and pricing teams to translate business requirements into ML solutions.
• Implement and monitor MLOps practices in cloud environments to keep models performing in production.
• Run exploratory analysis and customer segmentation on transactional, digital behavior and geospatial data.
• Document technical work and explain analytical results clearly to non-technical stakeholders.

What you’ll bring

• 5+ years in Data Science or Machine Learning Engineering, with a strong focus on time series forecasting and predictive modeling.
• Python or R for statistical modeling and machine learning.
• Hands-on experience deploying and monitoring ML models in a major cloud (GCP, Azure or AWS).
• MLOps and data pipeline experience.
• Strong statistics foundation: time series models, survival analysis, customer segmentation.
• Advanced SQL and relational databases.
• Experience leading technical projects or mentoring junior data professionals.
• Degree in Statistics, Engineering, Data Science, Mathematics or a related quantitative field.
• C1 English or higher.

Nice to have

Power BI, GIS / geospatial analytics.

Why this role

You’ll own models that directly drive pricing, demand and customer decisions, with room to set the standard for how ML runs in production across the team.