Data Scientist

Evlo AI; Chicago (IL); On-site; USD 120,000 - 180,000; Full time

Job summary

Evlo AI is seeking a hands-on data scientist to turn messy real-world data into production-ready models that drive measurable business decisions. You will work with ML engineers and data engineers across the full modeling lifecycle using Python, SQL, Spark, and cloud tooling.

You will frame business problems as testable ML questions, design controlled experiments, and build predictive models with scikit-learn, XGBoost, and PyTorch, collaborating across teams to productionize features and

Qualifications

• 3–6 years of experience in data science or applied ML with at least one model in production.
• Expert-level SQL and strong Python (pandas, NumPy, scikit-learn).
• Hands-on experience with A/B testing and causal inference; able to explain uplift models or difference-in-differences.
• Experience processing large datasets with Spark, Databricks, or equivalent distributed tooling.
• Master's degree in statistics, CS, economics, or related field (or equivalent practical experience).
• Strong written and verbal communication; able to defend methodology for executives.
• Bonus: exposure to LLM-based analytics or retrieval systems or experimentation platforms.

Responsibilities

• Frame ambiguous business problems as testable ML and statistical questions, and communicate tradeoffs to technical and non-technical stakeholders
• Design and run controlled experiments (A/B tests, quasi-experimental designs), computing sample sizes, guardrail metrics, and causal estimates with rigor
• Build, train, and validate predictive models - gradient boosting, logistic regression, time-series forecasting, and NLP classifiers - using scikit-learn, XGBoost, and PyTorch
• Develop feature pipelines in Python and PySpark, partnering with data engineers to ensure reliability from raw data through training and inference
• Partner with ML engineers to productionize models, including feature stores, batch/online scoring, and monitoring for drift and performance decay
• Communicate results through clear analyses, technical write-ups, and visualizations using SQL, notebooks, and BI tooling Looker or Tableau

Skills

SQL

Python

A/B testing

Causal inference

Communicating findings

Spark

Education

Master's degree in statistics | CS | economics

Tools

Databricks

dbt

Airflow

MLflow

Looker/Tableau

Job description

About The Role

The role is for a hands-on data scientist who turns messy, real-world data into models that ship to production and drive measurable business decisions - not dashboards that sit unread.

You will work with ML engineers and data engineers across the full modeling lifecycle: problem framing, experimentation, statistical validation, and deployment, in a stack built on Python, SQL, Spark, and modern cloud tooling.

Key Responsibilities

• Frame ambiguous business problems as testable ML and statistical questions, and communicate tradeoffs to technical and non-technical stakeholders
• Design and run controlled experiments (A/B tests, quasi-experimental designs), computing sample sizes, guardrail metrics, and causal estimates with rigor
• Build, train, and validate predictive models - gradient boosting, logistic regression, time-series forecasting, and NLP classifiers - using scikit-learn, XGBoost, and PyTorch
• Develop feature pipelines in Python and PySpark, partnering with data engineers to ensure reliability from raw data through training and inference
• Partner with ML engineers to productionize models, including feature stores, batch/online scoring, and monitoring for drift and performance decay
• Communicate results through clear analyses, technical write-ups, and visualizations using SQL, notebooks, and BI tooling (Looker or Tableau)

What We Are Looking For

• 3–6 years of experience in data science or applied machine learning, with at least one model taken from prototype to production
• Expert-level SQL and strong Python for data manipulation and modeling (pandas, NumPy, scikit-learn)
• Hands-on experience with A/B testing and causal inference techniques; you can explain when an uplift model or difference-in-differences is the right tool
• Experience processing large datasets with Spark, Databricks, or equivalent distributed tooling
• Master's degree in statistics, computer science, economics, or a related quantitative field (or equivalent practical experience)
• Strong written and verbal communication - able to defend methodology and simplify findings for executive audiences
• Bonus: experience with dbt, Airflow, MLflow, or experimentation platforms (e.g., in-house A/B tooling); exposure to LLM-based analytics or retrieval systems