Senior Data Scientist — Predictive Analytics & Insights

Remote Jobs; United States; Remote; USD 90,000 - 130,000; Full time

Job summary

Softeq is seeking a data analytics professional to build predictive models and dashboards, aligning metrics with business needs across large enterprise data sources.

You'll work with Python ecosystems (pandas, scikit-learn), Spark SQL/PySpark, and Databricks to develop scalable analytics products and deliver clear guidance to non-technical stakeholders. The role emphasizes handling time-series data, model documentation, and collaboration with business teams.

Qualifications

• Must-have: Strong Python analytics experience with pandas and scikit-learn.
• Must-have: Proficient in Spark SQL and PySpark for large tables.
• Must-have: Databricks environment experience with notebooks, jobs, and time travel.
• Must-have: Knowledge of medallion data layers and source correctness.
• Must-have: Statistics and time-series methods with solid experiment design.
• Must-have: Experience handling enterprise data quality issues.
• Must-have: Ability to explain results to non-technical stakeholders.

Responsibilities

• Explore operational and financial data, frame hypotheses and test them.
• Build predictive and analytical models for delays, congestion, costs, and variance.
• Engineer features and document their provenance across data layers.
• Work with historical states to ensure time-consistent training samples.
• Prepare inputs for analytics products: dashboards, activity analytics, executive summaries, trend analysis.
• Align metric definitions with semantic layer for consistent reports and APIs.
• Validate results with business stakeholders and produce model documentation.

Skills

Python

Pandas

Scikit-learn

Statistical libraries

Data visualization

Spark SQL

PySpark

Databricks

Time-series methods

Experiment design

Communication

Tools

Databricks

Job description

Softeq is seeking a data analytics professional to build predictive models and dashboards, aligning metrics with business needs across large enterprise data sources.

You'll work with Python ecosystems (pandas, scikit-learn), Spark SQL/PySpark, and Databricks to develop scalable analytics products and deliver clear guidance to non-technical stakeholders. The role emphasizes handling time-series data, model documentation, and collaboration with business teams.