Senior Data Scientist Needed for Data Pipeline Build Initiative

BlueSky Ventures

Contract · Remote · Flexible hours

About the role

BlueSky Ventures is scaling its B2B SaaS platform and needs a senior Data Scientist to drive multi‑tenant feature delivery. You will own the design and implementation of the Nimbus Analytics Engine, a new module that provides tenant‑specific predictive insights across the product suite.

Key responsibilities

• Architect and prototype the Nimbus Analytics Engine using Python, PySpark, and PostgreSQL to support isolated tenant data pipelines.
• Develop and validate machine‑learning models that predict churn and upsell opportunities for each tenant.
• Integrate model inference into existing REST APIs, ensuring low‑latency responses under multi‑tenant load.
• Collaborate with backend engineers to containerize models with Docker and orchestrate deployments via Kubernetes.
• Produce performance dashboards in JavaScript (D3.js) for internal stakeholders to monitor model drift.
• Deliver a proof‑of‑concept demo within eight weeks and iterate based on stakeholder feedback.

Must-have skills

• Advanced Python for data science (pandas, scikit‑learn, PyTorch).
• Strong SQL expertise with PostgreSQL, including partitioning for tenant isolation.
• Experience building and exposing models through RESTful services.
• Proficiency in data pipeline tools (Airflow, Spark) and cloud environments.
• Ability to translate business requirements into statistical models.

Nice to have

• Familiarity with multi‑tenant architecture patterns.
• Knowledge of CI/CD for ML models (MLflow, Kubeflow).