> Markdown version of [/jobs/ext/3995263-manager-senior-manager-data-science-1311](https://www.wearedevelopers.com/jobs/ext/3995263-manager-senior-manager-data-science-1311). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Manager/Senior Manager - Data Science (1311)

- **Company:** Axtria, Inc.
- **Location:** Thousand Oaks, CA, United States
- **Experience:** Expert
- **Salary:** $119,500.0 - $163,875.0
- **Contract:** Permanent contract
- **Skills:** Amazon Web Services, Microsoft Azure, Information Engineering, Python (Programming Language), Machine Learning, Tensorflow, SQL Databases, Feature Engineering, Pytorch, SHAP (Shapley Additive Explanations), Deep Learning, Model Validation, Pyspark, Xgboost, Transformer Architectures, Machine Learning Operations, Recurrent Neural Networks, Databricks
- **Published:** October 28, 2026
- **Apply:** https://www.thejobnetwork.com/job/69142d2e-b08e-4f75-bc52-800e575da9d8/managersenior-manager-data-science-

## About the Role

* 5+ years of hands-on experience in data science, preferably US pharma/biotech
 * Strong Python, PySpark, PyTorch/TensorFlow, and AWS/Azure skills.
 * Practical experience in Transformer architectures and sequence modeling

## Description

* Build and optimize ML models for pharma commercial use cases, including patient journey modeling, patient identification, treatment progression, churn prediction, HCP targeting, and Next Best Action (NBA).
 * Develop advanced deep learning and sequence models, including Transformers, LSTM/GRU, and attention-based architectures, to analyze longitudinal patient journeys and temporal patterns.
 * Design HCP/patient-level datasets by integrating claims, lab, specialty pharmacy, hub, CRM, promotional, and sales data, with strong expertise in temporal feature engineering and sequence preparation.
 * Apply traditional ML techniques (XGBoost, LightGBM) alongside deep learning, focusing on model evaluation, benchmarking, and explainability (SHAP).
 * Build end-to-end ML pipelines using Databricks, PySpark, SQL, and MLflow, covering data engineering, model training, validation, monitoring, and deployment.
 * Translate complex analytical findings into actionable insights for brand, sales operations, and commercial stakeholders.