Senior Data Scientist: Predictive Analytics & BI

Softeq; Región Centro; On-site; MXN 600,000 - 900,000; Full time

Job summary

Softeq is seeking an analytics-minded professional to join our data team. You will explore operational data, frame hypotheses, and build predictive models to improve project efficiency and cost management.

The role involves engineering features, ensuring data provenance, and generating actionable dashboards and executive summaries for business stakeholders. The ideal candidate will have strong Python analytics skills, experience with Spark SQL and PySpark on large datasets, and hands-on

Qualifications

• Proficient in Python for data analysis and modeling.
• Experience with Spark SQL and PySpark on large datasets.
• Hands-on Databricks experience for notebooks and jobs.
• Understanding of medallion data architecture and data lineage.
• Strong statistics, time-series methods, and experiment design.
• Ability to explain results to non-technical stakeholders.
• Experience with enterprise data from systems of record.

Responsibilities

• Explores operational and financial data, frames hypotheses and tests them.
• Builds predictive and analytical models: delays and durations, congestion, cost, plan-versus-actual variance.
• Engineers features over the curated data layers and documents their meaning and provenance.
• Works with historical data states so that a training sample reflects what was known at the time of the event rather than what is known now.
• Prepares the inputs behind analytics products: KPI dashboards, user activity analytics, executive summaries, trend analysis.
• Aligns metric and calculation definitions with the semantic layer so figures agree across reports, APIs and interfaces.
• Validates results with business stakeholders and produces model documentation.

Skills

Analytical Python

Spark SQL

PySpark

Databricks

Time-series

Model validation

Data wrangling

Stakeholder comms

Tools

Pandas

scikit-learn

SQL

Job description

Softeq is seeking an analytics-minded professional to join our data team. You will explore operational data, frame hypotheses, and build predictive models to improve project efficiency and cost management.

The role involves engineering features, ensuring data provenance, and generating actionable dashboards and executive summaries for business stakeholders. The ideal candidate will have strong Python analytics skills, experience with Spark SQL and PySpark on large datasets, and hands-on