Senior Data Scientist for Multi-Region Data Pipeline Build

DataPro Services

Contract · Remote · Flexible hours

About the role

DataPro Services is modernizing the performance and reliability of its flagship customer‑facing analytics platform. As a Senior Data Scientist you will lead the redesign of the predictive scoring engine, codenamed "PulsePredict", ensuring low‑latency responses and robust fault tolerance across high‑traffic endpoints.

Key responsibilities

• Audit and refactor the existing Spark‑based pipelines to reduce end‑to‑end latency by 30%.
• Implement real‑time feature extraction using Kafka Streams and PySpark, integrating with the PulsePredict microservice.
• Design and execute A/B testing frameworks in Python to validate model stability under load.
• Collaborate with the DevOps team to containerize models with Docker and orchestrate via Kubernetes for auto‑scaling.
• Develop monitoring dashboards in Grafana that track model drift, latency, and error rates.
• Document data lineage and version control using MLflow for reproducibility.

Must-have skills

• Advanced Python for data manipulation, modeling, and automation.
• Proficient with PostgreSQL for feature store queries and data warehousing.
• Experience building and consuming REST APIs for model serving.
• Strong background in statistical modeling, time‑series analysis, and performance optimization.
• Familiarity with cloud environments (AWS/GCP) and container orchestration.

Nice to have

• Knowledge of CI/CD pipelines for ML model deployment.
• Exposure to serverless architectures such as AWS Lambda.