Python Engineer (Data / ML)

About Gleantap

Gleantap is a customer engagement platform powering fitness, wellness, and service businesses. We’re evolving into an AI-native platform, where intelligent agents predict churn, upsell opportunities, and automate member engagement.

We’re looking for a Python Data/ML Engineer who can bridge the gap between data engineering and applied machine learning, building pipelines, training models, and deploying them into production at scale.

Responsibilities

* Design and build data pipelines to transform raw events (visits, purchases, campaigns) into usable features.

* Define and compute labels (e.g., churn, upsell, lead quality) from historical events.

* Develop and train ML models (e.g., churn prediction, upsell propensity, lead scoring) using Python (scikit-learn, LightGBM, XGBoost).

* Build real-time inference services to serve predictions into production systems.

* Set up retraining and monitoring pipelines (Airflow, MLflow, or similar).

* Collaborate with backend engineers to integrate model outputs into Gleantap workflows.

* Ensure data quality, reproducibility, and compliance (HIPAA for healthcare customers).

Requirements

* 3–5+ years of experience in data engineering or applied ML.

* Strong proficiency in Python, SQL, and one or more ML libraries (scikit-learn, LightGBM, XGBoost, PyTorch).

* Experience with data pipelines (Airflow, dbt, or custom ETL).

* Comfortable with event-driven systems (Kafka, Redis, ClickHouse or similar OLAP).

* Understanding of ML lifecycle: training, serving, monitoring, retraining.

* Ability to design time-based labels (avoiding data leakage).

* Strong problem-solving skills and eagerness to work in a startup environment.

Nice-to-Haves

* MLOps tools (MLflow, BentoML, Ray Serve).

* Experience with bandit algorithms, A/B testing, or uplift modeling.

* Prior work with customer engagement, CRM, or subscription businesses.