Sr Data Scientist -CDP platform

The ideal candidate will have hands-on experience with model development and a deep understanding of customer data ingestion, real-time data pipelines, and AI-driven marketing strategies. You will be responsible for leveraging advanced analytics and machine learning to enable data-driven decision-making and hyper-personalized marketing at scale.

Key Responsibilities

• Model Development
  

Daily Tasks:

• Design, prototype and iterate on ML models (segmentation, churn, personalization, propensity, campaign response) using Python and relevant ML frameworks.
• Ingest and preprocess customer data from batch and real-time sources; implement feature engineering and testing.
• Run experiments, evaluate metrics, and maintain model training pipelines to ensure reproducibility.
• Prepare model artifacts, documentation and handoffs for deployment teams (Martech, engineering).
• Participate in daily stand-ups with cross-functional teams and provide model status updates.
  

Measurable Expectations (targets):

• Deliver 2–4 production-ready models per quarter aligned to prioritized business use cases.
• Achieve and maintain agreed performance thresholds (e.g., AUC/precision/recall or business KPIs) as defined with stakeholders prior to deployment.
• Document and version 100% of model code, data schemas and feature definitions for every production model.
• Automate training and deployment pipelines to reduce manual intervention by at least 50% versus baseline.
  

Additional Responsibilities:

• Translate model insights into actionable marketing strategies that enhance ROI and customer experience.
• Collaborate with Martech, digital, and commercial teams to operationalize models into platforms and workflows.
• Establish monitoring, retraining, and governance processes to ensure sustained model accuracy and business value.
• Deep QA & Model Validation
  

Daily Tasks:

• Execute end-to-end validation checks for models pre-deployment (data ingestion, schema, feature engineering, labels, performance metrics).
• Run automated and manual tests to detect data drift, label drift and performance regressions; triage anomalies and escalate as needed.
• Maintain validation notebooks, test suites and dashboards that capture validation outcomes and issues.
• Document validation findings, track remediation actions and confirm fixes before sign-off.
• Work with engineering/DevOps to ensure CI/CD and monitoring integrations are in place for each model.
  

Measurable Expectations (targets):

• Validate 100% of models prior to production deployment and ensure documented sign-off for each release.
• Maintain validation coverage such that >95% of critical features and model pathways have automated tests and checks.
• Detect and surface drift within 24–72 hours of onset and close high-priority validation incidents within 48 hours of identification.
• Produce validation reports/dashboards for stakeholders within 2 business days of model evaluation completion.
  

Other QA Responsibilities:

• Assess integration points (downstream outputs, GUI integration) to ensure model outputs are correctly consumed by products and campaigns.
• Support development of dashboards and reports to track validation progress, outcomes, and risks.
• Ensure every module is accurate, reliable, and business-aligned prior to deployment.
  

Required Qualifications

• Master's degree in Data Science, Statistics, Computer Science, or related field.
• 4 to 6 years of experience in data science, model validation, and applied machine learning.
• Proven expertise in Python, SQL, and ML frameworks (scikit-learn, TensorFlow, PyTorch).
• Experience with QA and drift monitoring frameworks for ML models.
• Familiarity with big data platforms and cloud ecosystems such as Databricks, Spark, Snowflake, AWS, Azure, or GCP.
• Strong communication skills to convey complex insights to both technical and business stakeholders.
• Experience leading junior data scientists.
• Detail-oriented with a structured approach to QA, documentation, reporting, and dashboarding.