Data Scientist

Role

As a Data Scientist, you will build the models that turn customer data into decisions - forecasting, optimization, measurement, and the analysis that tells us whether any of it is working.

You'll work across the full lifecycle: understanding a business problem, exploring the data, developing and validating models, and partnering with engineers to get them into production. You'll also work directly with customer data and customer-facing teams, which means your analysis needs to hold up under scrutiny from people whose decisions depend on it.

This role is a strong fit for someone earlier in their career who wants real ownership quickly. You'll get direct mentorship from our Co-Founder & CAIO and senior engineers, and the scope to grow fast.

Responsibilities

Modeling & Analysis

• Develop, validate, and iterate on models for forecasting, optimization, anomaly detection, and measurement.
• Perform exploratory analysis on complex customer datasets to surface patterns worth acting on.
• Design and analyze experiments; build the measurement approaches that quantify business impact.
• Establish rigorous validation practices - backtesting, holdouts, and honest error analysis.

Production & Collaboration

• Partner with ML and data engineers to move models from notebook to production.
• Contribute to feature engineering, evaluation pipelines, and model monitoring.
• Write clean, reproducible Python that other people can read and build on.

Business Impact

• Translate business questions into analytical problems, and analytical results back into recommendations.
• Communicate findings clearly to internal teams and customers, including non-technical audiences.
• Follow deployed models into the real world and help make sure they're delivering what we promised.

All About You

• Experience developing and validating models on real, messy data - through internships, prior roles, or substantive project work.
• Solid foundation in statistics and machine learning: regression, time series, tree-based methods, experimental design.
• Strong Python (pandas, scikit-learn, and the surrounding ecosystem) and strong SQL.
• Curiosity about the business problem behind the data, not just the modeling technique.
• Clear communication - you can explain what you did, why, and what it means, to someone who doesn't do this for a living.
• Strong problem-solving skills, adaptability, and a "hacker" mentality.
• Eagerness to learn quickly in a startup environment.

Nice to have

• Exposure to CPG, retail, or consumer brand data.
• Experience with Spark, cloud platforms (AWS or similar), or orchestration tools.
• Familiarity with LLMs and their practical use in analytical workflows.

Benefits & Perks

Location

• Hybrid role based in New York City; open to remote U.S. candidates willing to travel monthly to our NYC office.
• equal opportunity employer