This is a fully remote position, open to applicants in Argentina.

📋 Description

• Develop and deploy predictive models for churn, lifetime value, and payer propensity.

• Explore models in Databricks and enable real-time serving within the advertising mediation stack.

• Create and maintain ML pipelines in production using Airflow, Spark/Databricks, and AWS.

• Implement training, validation gates, and model promotions.

• Monitor model calibration, drift, and impact in production.

• Measure impact through A/B testing.

• Collaborate on generative AI initiatives, including integrations with internal APIs, evaluation sets, observability, and human-in-the-loop controls.

• Build tools and context for coding agents.

• Work together with Data Engineering, Backend, SDK, AdOps, and Product teams to turn models into product functionalities.

⛳️ Requirements

• Proven experience (3+ years) as a Machine Learning Engineer, Data Scientist, or in a similar role, including deploying and maintaining models in production.

• For Senior level, 5+ years of experience with a track record of leading end-to-end initiatives, guiding technical decisions, and mentoring other engineers.

• Proficiency in Python and SQL, including pandas or Polars and scikit-learn.

• Experience with classification, regression, and ranking models.

• Strong foundation in statistics: probability calibration, imbalanced classification, evaluation metrics beyond accuracy, and A/B testing.

• Practical experience with LLMs: tool calling, prompt design, output evaluation of agents, and coding agents.

• Familiarity with Spark/Databricks, Airflow, and AWS.

• Ability to troubleshoot models and data in production.

• Fluent Spanish is a must.

• Desirable: experience in AdTech, mobile games, or app monetization.

• Desirable: knowledge of reinforcement learning, multi-armed bandits, and contextual bandits.

• Desirable: experience with Pydantic AI, LangGraph, or Model Context Protocol (MCP).