Data Scientist

edkey; Chicago (IL); Hybrid; USD 90,000 - 115,000; Full time

Job summary

edkey, located in Chicago, IL, is hiring a Data Scientist to work on demand forecasting and analytics. In this role, you will build ML models to support retail operations and translate analyses into insights for stakeholders.

The ideal candidate will have at least 2 years of experience in data science, strong Python and SQL skills, and the ability to communicate technical findings effectively. This position offers a hybrid work model requiring in-office presence approximately once every two weeks.

Qualifications

• 2+ years of hands-on experience in data science, quantitative analysis, or ML engineering.
• Strong Python skills for data manipulation, modeling, and analysis.
• Clear written communication skills for explaining analytical findings.

Responsibilities

• Build, test, and maintain ML models for demand forecasting.
• Translate data into actionable insights for non-technical stakeholders.
• Diagnose forecasting errors and propose remediation plans.

Skills

Python programming

SQL

Model building

Feature engineering

Statistical analysis

Education

Bachelor’s degree or equivalent experience

Tools

Snowflake

Jupyter

scikit-learn

Job description

What You'll Do

This is a hands‐on Data Scientist role focused on demand forecasting, feature engineering, and analytics to support multi‑location retail operations. You will build, test, and maintain ML models, engineer features, and translate data into actionable insights for non‑technical stakeholders. You will work closely with the Manager of Data Engineering, AI & ML and contribute to a growing, production‑focused data science function.

• Build, validate, and refine demand forecasting models across daily, weekly, monthly, and quarterly horizons for retail, wholesale, and emerging business channels.
• Engineer features for a Snowflake‑based feature store using retail sales history, inventory movement, weather, customer demographics, and external signals.
• Develop, backtest, and compare new model candidates using the client’s established backtesting framework; interpret results to inform inventory and promotion decisions.
• Diagnose forecasting errors and anomalies (data drift, structural breaks, new store openings, regulatory changes) and propose remediation plans.
• Apply dimensionality reduction and PCA to identify primary feature importance.
• Design and execute analytical studies that answer operational business questions and enable repeatable, parameterized frameworks.
• Build reusable analytical frameworks on top of curated data layers (retail sales, inventory, customer, loyalty, workforce) to promote self‑service.
• Contribute to quasi‑experimental analyses: pre/post launch performance, store cohort comparisons, product mix attribution, and discount effectiveness.
• Translate analytical findings into clear written summaries and visualizations for business stakeholders.
• Participate in roadmap and design discussions, helping prioritize signals, data gaps, and model architectures to explore.
• Learn and work with the production data stack (Snowflake, dbt, Dagster) and related AI tooling over time.

Qualifications

• 2+ years of hands‑on experience in data science, quantitative analysis, or ML engineering with demonstrable work in model building, feature engineering, or statistical analysis.
• Strong Python skills for data manipulation, modeling, and analysis (pandas, scikit‑learn, statsmodels, or equivalent). Experience developing in Jupyter or similar.
• Strong SQL skills — comfortable authoring complex queries, aggregating at multiple grains, joining tables, and debugging data quality issues.
• Working experience with supervised and unsupervised ML methods (gradient boosting, time series models, random forest, decision trees, etc.).
• Clear written communication skills to explain analytical findings and recommended actions to non‑technical stakeholders.
• Intellectual curiosity and a bias toward figuring things out in messy, multi‑state retail data environments.
• Bachelor’s degree or equivalent experience.

Preferred Qualifications

• Experience with time series forecasting methods (ARIMA, Prophet, LightGBM/XGBoost for tabular time series, or similar).
• Familiarity with advanced ML techniques (Bayesian inference, deep learning, clustering).
• Experience with feature store concepts or structured feature engineering pipelines.
• Exposure to Snowflake, Snowpark, cloud data warehouses, and dbt or layered data warehouse patterns (raw → refined → curated).
• Experience prototyping or productionizing data products (Streamlit, dashboards, lightweight apps).
• Basic familiarity with LLM‑powered tooling or AI agent frameworks.
• Background in retail, CPG, consumer analytics, or multi‑location operations.

Compensation & Benefits

• The pay range is $90,000—$115,000 USD, dependent on experience, qualifications, and/or location of the role.
• Positions may be eligible for a discretionary annual incentive program driven by organization and individual performance.
• Benefits and additional compensation details will be provided by the confidential client during the hiring process.

Work Location & Schedule

• Hybrid — requires in‑office presence approximately 1 day every 2 weeks at an office in River North, Chicago, IL.

Additional Requirements & Legal Notices

• Employment may be contingent upon successful background checks and any industry‑required screenings.
• Must meet industry‑specific legal or regulatory requirements to work in the role; where applicable, candidates must be at least 21 years of age in accordance with industry and state regulations.
• Applicants may be required to demonstrate authorization to work in the United States; the confidential client will comply with applicable employment and immigration laws.
• This job posting is intended to comply with applicable U.S. federal, state, and local employment laws.

Equal Opportunity & Hiring Transparency

CareerTakes and our client are Equal Opportunity Employers committed to building a diverse and inclusive workforce. We prohibit discrimination or harassment of any kind. To support a fair and efficient hiring process, AI tools may be used to assist with application review or resume screening. These tools do not replace human decision‑making. Final hiring decisions are made by people.

If you have questions about how your data is used, please contact us directly.