Machine Learning Engineer

We are seeking a Senior Machine Learning Engineer to own the design, deployment, and maintenance of production ML systems that power automated decisioning across marketing and customer-facing workflows. The right candidate pairs strong engineering discipline with a commercial mindset and can translate model output into measurable business impact. Rate: up to 25 USD/h Engagement: full-time (40h/week) Contract length: 12 months English: min. B2+ Key Responsibilities Build, deploy, and own production-grade ML models in Python, with accountability for reliability and maintainability Integrate model predictions with external platforms via APIs to trigger automated actions such as campaign optimization, recommendations, and pricing Develop feature engineering, data validation, and reproducible data transformation pipelines using SQL and BigQuery Run and scale ML workloads on GCP using Vertex AI, Pub/Sub, Cloud Run, and Composer/Airflow Train, tune, and evaluate gradient boosting models against business-relevant metrics Calibrate model outputs and assess the downstream impact of prediction errors on business decisions Required Qualifications 5+ years of hands-on ML engineering experience in Python, with ownership of deployed models and production-grade code Proven experience integrating ML predictions with external platforms via API to drive automated actions Strong SQL and BigQuery skills for feature engineering, data validation, and reproducible transformations Hands-on experience operating ML workloads on GCP: Vertex AI, Pub/Sub, Cloud Run, Composer/Airflow Expertise in gradient boosting models (LightGBM, CatBoost, XGBoost), including tuning and evaluation against business-relevant metrics Ability to calibrate predictions and quantify how model errors affect downstream decisions Strongly Preferred Entity resolution or identity resolution experience Propensity, churn/retention, segmentation, or LTV modeling within e-commerce or DTC Server-side conversion tracking via major ad platform APIs Bayesian methods and probabilistic customer models (BG/NBD, Gamma-Gamma) Nice to Have Experimentation, causal inference, or bandit methods applied to marketing use cases Docker, Terraform, and CI/CD for pipeline automation Familiarity with AI-assisted development tools