Nisum is a leading global digital commerce firm headquartered in California, with services spanning digital strategy and transformation, insights and analytics, blockchain, business agility, and custom software development. Founded in 2000 with the customer-centric motto “Building Success Together®,” Nisum has grown to over 1,800 professionals across the United States, Chile,Colombia, India, Pakistan and Canada. A preferred advisor to leading Fortune 500 brands, Nisum enables clients to achieve direct business growth by building the advanced technology they need to reach end customers in today’s world, with immersive and seamless experiences across digital and physical channels.
Key Requirements:
We are looking for a highly skilled and analytical Data Scientist / Engineer with strong experience in Python, SQL, data engineering, causal inference, forecasting, and production machine learning. The ideal candidate will be responsible for building scalable data solutions, developing and evaluating analytical models, and taking machine learning models from zero-to-one through production deployment.
What You'll Do:
- Develop and maintain production-grade Python solutions for data processing, analytics, modelling, and machine learning use cases.
- Work extensively with SQL and BigQuery or similar cloud-based data warehouses to extract, transform, analyze, and manage large datasets.
- Design and implement robust ETL processes, data pipelines, and data models to support analytical and machine learning workflows.
- Build and manage data pipelines using orchestration tools such as Airflow, Dagster, Cloud Composer, or similar technologies.
- Develop reliable and scalable data transformations using dbt-style frameworks, including data testing and validation.
- Apply advanced Causal Inference techniques, including Difference-in-Differences, Synthetic Control, Counterfactual analysis, and related methodologies.
- Develop and evaluate forecasting and analytical models using appropriate evaluation methodologies, time-based backtesting, and techniques to identify and prevent data leakage.
- Work on Entity Resolution / Entity Matching problems to accurately identify and link entities across multiple datasets and data sources.
- Take analytical and machine learning models from zero-to-one, including development, validation, productionization, and ongoing improvement.
- Collaborate closely with business stakeholders to understand business problems and translate complex analytical findings into clear, actionable insights.
Data Science & Machine Learning:
- Apply statistical and machine learning techniques to solve complex business and analytical problems.
- Develop models for forecasting, causal analysis, demand modelling, and other business-critical use cases.
- Perform rigorous model evaluation, including time-based backtesting, forecasting metrics, and analysis of potential data leakage.
- Build production-ready modelling workflows with a strong focus on reliability, scalability, and maintainability.
Data Engineering & Modelling:
- Design and implement scalable ETL workflows and data pipelines.
- Build and maintain data models and transformations using modern data engineering practices.
- Work with BigQuery or similar data warehouse technologies to manage and analyze large-scale datasets.
- Use Airflow, Dagster, Cloud Composer, or similar orchestration platforms to schedule, monitor, and manage data workflows.
- Implement dbt-style transformations, data quality checks, and automated data testing.
What You Know:
- Strong experience with Python and SQL, including production-grade Python development.
- Hands-on experience working with BigQuery or similar data warehouse technologies.
- Strong understanding of Causal Inference, including Difference-in-Differences, Synthetic Control, Counterfactuals, and related methodologies.
- Experience with model evaluation, time-based backtesting, forecasting, and identifying data leakage.
- Hands-on experience with ETL, data pipelines, and data modelling.
- Experience with Airflow, Dagster, Cloud Composer, or similar workflow orchestration tools.
- Knowledge of dbt-style transformations and data testing.
- Experience with Entity Resolution / Entity Matching.
- Proven experience taking analytical or machine learning models from zero-to-one and deploying them into production.
- Strong communication skills, with the ability to explain complex analytical results and technical concepts to business stakeholders.
Nice to Have:
- Experience with retail demand modelling and forecasting.
- Experience with price elasticity or promotion lift modelling.
- Experience working within Grocery, CPG, or Trade Promotion environments.
- Experience with multi-tenant model deployment.
- Experience with AWS, GCP, or Azure cloud platforms.
- Experience with LLM-based document or data extraction.
- Previous experience working in an early-stage startup environment.
Education:
Bachelor’s or Master’s degree in Computer Science, Data Science, Statistics, Mathematics, Engineering, or a related field.