Production ML Scientist — Real-Time Personalization & Offers

Hidden Jobs; United States; Remote; USD 140,000 - 180,000; Full time

Job summary

Hidden Jobs is hiring a Data Scientist to productionize ML models and ship live product features. The role partners with Product, Engineering, and Lifecycle Marketing to deploy models starting with a personalization engine for paywalls and lifecycle offers.

You will help establish real-time, low-latency serving patterns on GCP and drive end-to-end ML delivery from problem framing to monitoring.

Qualifications

• 4-7 years as a data scientist or ML engineer with production-grade models.
• Strong Python for ML, including scikit-learn and gradient boosting libraries (XGBoost/LightGBM).
• Hands-on cloud ML platform experience (prefer GCP).
• Solid SQL and dbt/BigQuery experience.
• Software engineering basics: Git, code reviews, testing, CI/CD.
• Experience with causal inference or uplift modeling in pricing or personalization.

Responsibilities

• Build, validate, and deploy ML models running inside the product, from framing to monitoring and retraining.
• Design and ship the personalized discounting model with an evaluation framework.
• Stand up low-latency model serving on GCP and define feature flow between batch and real-time streams.
• Implement monitoring for drift, staleness, and prediction quality in live models.
• Translate product problems into modeling problems and define API contracts for engineering.
• Design causal and uplift models and run controlled experiments to prove incremental lift.

Skills

Python for ML

SQL

Production ML

Causal inference

English fluency

Model monitoring

Experiment design

Team collaboration

Education

Bachelor's degree in CS/ Stats / Engineering

Tools

GCP

Vertex AI

BigQuery

dbt

Git

Cloud Run/Functions

XGBoost/LightGBM

Job description

Hidden Jobs is hiring a Data Scientist to productionize ML models and ship live product features. The role partners with Product, Engineering, and Lifecycle Marketing to deploy models starting with a personalization engine for paywalls and lifecycle offers.

You will help establish real-time, low-latency serving patterns on GCP and drive end-to-end ML delivery from problem framing to monitoring.