Senior Data Scientist

Convo; Islamabad; On-site; PKR 1,800,000 - 3,000,000; Full time

Job summary

Convo in Islamabad, Pakistan seeks a Data Scientist with 5+ years of experience to develop scalable, data-driven solutions focusing on time-series forecasting, predictive analytics, and advanced data manipulation. Strong Python, pandas, NumPy, Matplotlib, PySpark, Databricks, Git, and Azure DevOps skills are required, along with solid statistics and data analysis fundamentals.

You will collaborate with stakeholders and data engineers to translate business problems into analytical solutions,

Qualifications

• Develop, evaluate, and deploy time-series forecasting models for business and commercial applications.
• Build predictive analytics solutions to support data-driven decision-making.
• Perform data preparation, cleansing, transformation, and feature engineering using Python and pandas.
• Work with large datasets using PySpark and optimize data processing workflows.
• Develop and maintain data pipelines and analytical workflows in Databricks.
• Analyze trends, seasonality, outliers, and other patterns in historical data.
• Select appropriate forecasting and predictive modeling techniques based on business requirements.
• Validate model performance using relevant statistical and business metrics.
• Collaborate with business stakeholders, data engineers, and technology teams to translate business problems into analytical solutions.
• Use Azure DevOps for source control, work-item tracking, CI/CD, and collaborative development.
• Document analytical methodologies, assumptions, code, and model results clearly.
• Monitor model performance and recommend improvements when data or business conditions change.
• Follow established standards for code quality, testing, version control, and deployment.

Responsibilities

• Develop time-series forecasting models for commercial use.
• Create predictive analytics solutions to guide business decisions.
• Process and feature engineer data with Python/pandas.
• Optimize PySpark-based data pipelines for performance.
• Build and maintain Databricks notebooks, jobs, and data workflows.
• Assess trends and seasonality to improve forecasts.
• Evaluate models using business metrics and statistics.
• Collaborate with data teams to translate requirements into models.
• Document methodologies, code, and results clearly.
• Monitor production models and implement improvements as needed.

Skills

Analytical thinking

Problem solving

Communication skills

Education

Bachelor’s or Master’s degree in Data Science, Computer Science, Statistics, Mathematics, Engineering, or related field

Tools

Python

pandas

NumPy

Matplotlib

PySpark

Databricks

Git

Azure DevOps

SQL

Linux

Job description

Job Summary

We are looking for a Data Scientist with 5+ years of overall professional experience to develop scalable, data-driven solutions focused on time-series forecasting, predictive analytics, and advanced data manipulation. The ideal candidate will have strong hands-on experience with Python, pandas, NumPy, Matplotlib, PySpark, Databricks, Git, and Azure DevOps, along with a solid understanding of statistical modeling and data analysis principles.

Required Qualifications

• Develop, evaluate, and deploy time-series forecasting models for business and commercial applications.
• Build predictive analytics solutions to support data-driven decision-making.
• Perform data preparation, cleansing, transformation, and feature engineering using Python and pandas.
• Work with large datasets using PySpark and optimize data processing workflows.
• Develop and maintain data pipelines and analytical workflows in Databricks.
• Analyze trends, seasonality, outliers, and other patterns in historical data.
• Select appropriate forecasting and predictive modeling techniques based on business requirements.
• Validate model performance using relevant statistical and business metrics.
• Collaborate with business stakeholders, data engineers, and technology teams to translate business problems into analytical solutions.
• Use Azure DevOps for source control, work-item tracking, CI/CD, and collaborative development.
• Document analytical methodologies, assumptions, code, and model results clearly.
• Monitor model performance and recommend improvements when data or business conditions change.
• Follow established standards for code quality, testing, version control, and deployment.

Required Qualification & Skills

• Bachelor’s or master’s degree in Data Science, Computer Science, Statistics, Mathematics, Engineering, or a related field.
• Strong programming skills in Python, with 5+ years of relevant professional experience.
• Advanced proficiency in pandas, including data cleansing, reshaping, merging, aggregation, group-based operations, and efficient manipulation of large datasets.
• Strong working knowledge of NumPy for numerical computing, array operations, and efficient data processing.
• Experience using Matplotlib to create clear and insightful visualizations for exploratory analysis and model evaluation.
• Practical experience with time-series forecasting techniques, including trend and seasonality analysis, lag features, rolling statistics, and forecast evaluation.
• Strong understanding of predictive analytics, statistical analysis, and model validation.
• Hands-on experience with PySpark for distributed data processing.
• Experience working with Databricks notebooks, jobs, clusters, and data workflows.
• Familiarity with SQL for data extraction, joining, aggregation, and analysis.
• Experience using Git for source control, branching, merging, pull requests, and collaborative development.
• Experience using Azure DevOps for version control, task management, CI/CD processes, and release coordination.
• Working knowledge of Linux operating systems and familiarity with the command line.
• Understanding of data quality, reproducibility, and documentation best practices.
• Strong analytical, problem-solving, and communication skills.

Preferred Qualifications

• Experience applying forecasting and predictive analytics to sales, demand, pricing, revenue, or other commercial datasets.
• Familiarity with Azure data and analytics services.
• Experience with data visualization tools such as Power BI or similar platforms.
• Knowledge of model monitoring, performance tracking, and production support practices.
• Experience optimizing Python, pandas, SQL, or PySpark code for performance and scalability.
• Familiarity with Agile delivery practices and collaborative software development.

What We Have For You

Great compensation package, provident fund, paid leaves, EOBI, medical benefits for you and your family, free lunch, Bi-annual performance-tied increments & performance recognition awards and a great lean and agile work culture!

Convo endorses a culture of diversity in all aspects and aims to build a diverse team of amazing individuals!