Join #Ensiteam!

We are a company focused on custom software development and have been in the market for over 19 years. At Ensitech we are dedicated to finding highly specialized talent to work with large companies in the United States, Europe, and Canada.

We are seeking a Staff Data Scientist / Machine Learning Engineer to design, build, and own predictive Lifetime Value (pLTV) models that power critical business and marketing decisions. You will lead the full ML lifecycle, from feature engineering and model calibration to production deployment on GCP and real-time signal delivery into ad platforms and other external systems. This role combines deep expertise in gradient boosted trees and probabilistic customer models with strong software engineering practices. The ideal candidate has e-commerce or DTC experience and understands how model outputs drive downstream optimization and business value.

Responsabilities

Modeling & Calibration

Design, build, and maintain pLTV models using XGBoost, CatBoost, and probabilistic forecasting methods.
Develop and manage a tiered scoring framework that routes users to different models based on data availability and signal quality.
Create and optimize calibration frameworks that turn raw model outputs into business-ready values through normalization, scaling, and custom loss optimization.

Feature Engineering & Data Quality

Own feature engineering, building scalable feature datasets from transactional, behavioral, and engagement data.
Define and enforce feature quality standards so model inputs are reliable, relevant, and production-ready.
Develop and improve identity resolution processes to unify behavioral and transactional data across sources.

Monitoring & Impact

Monitor model performance, drift, and data distribution changes, and identify when retraining or adjustments are needed.
Analyze the impact of deployed models on downstream outcomes and detect feedback loops that may affect future accuracy.

Engineering & Infrastructure

Build, test, and maintain production-grade Python services and data pipelines for training, scoring, and signal delivery.
Apply strong engineering practices: automated testing, CI/CD, monitoring, idempotent processing, and deployment safeguards.
Operate and optimize ML workflows in the cloud using orchestration, scheduling, and distributed processing tools.
Ensure the reliability, accuracy, and scalability of ML systems that support critical business decisions.

Collaboration

Partner with data, engineering, and product stakeholders to improve data quality, model effectiveness, and platform scalability.

Must-haves

8+ years of experience in data science / ML, including 5+ years of hands-on ML engineering in Python with production-deployed models (not just notebooks or prototypes).
Production experience with gradient boosted trees (XGBoost, CatBoost, or LightGBM), including hyperparameter tuning, feature importance analysis, and evaluation beyond default metrics.
Strong SQL and BigQuery fluency: complex feature engineering queries, scheduled transformations, and data validation logic.
GCP production experience (Cloud Run, Airflow/Composer, Vertex AI, Pub/Sub), having deployed and maintained real ML workloads.
Solid understanding of model calibration: the difference between minimizing RMSE and maximizing business value, and how prediction errors compound in downstream optimization systems.
Outbound API integration experience, pushing model outputs into external systems that act on them (ad platforms, recommendation engines, pricing or bidding systems). This is required, not optional.

Strongly Preferred

E-commerce or DTC domain experience: customer lifetime value, purchase prediction, churn modeling, or customer segmentation for retail or subscription businesses.
Familiarity with probabilistic customer models (BG/NBD, Gamma-Gamma, or similar buy-till-you-die frameworks); strong Bayesian statistics foundations are equally valuable.
Ad platform signal engineering: Google Ads API (ConversionUploadService, Enhanced Conversions), Meta Conversions API (CAPI), or similar server-side event dispatch systems.
Identity resolution or entity matching: graph-based identity stitching, probabilistic matching, or CDP-style cross-device identity work.

Nice to Have

Terraform, CI/CD pipeline design, and Docker containerization for ML workloads.
Causal inference, A/B testing in ad spend environments, or multi-armed bandit allocation.
Familiarity with AI-assisted development tools (Claude Code, Cursor, or similar).

What do we offer?

100% remote opportunity.
Competitive salary and benefits.
Custom benefit package aligned to your experience and your needs.
Working with foreign clients.

Staff Data Scientist / Machine Learning...