Production Data Scientist: Scalable Features & Data Lake

Stealth Startup; New York (NY); On-site; USD 200,000 - 225,000; Full time

Benefits offered by this job

Relocation package

Competitive equity

Job summary

Stealth Startup in New York seeks a Data Scientist to build models and features powering our consumer graph and the agents that run on top of it. You own the path from raw data to a feature or model that an agent can call reliably at scale, and your work forms the foundation for other systems as we grow.

This role deploys constantly to production; you will own end-to-end development from data to production features, shaping a robust data lake, and ensuring outputs are ready for Minerva Agents

Qualifications

• 2-4+ years in data science or data engineering in data-heavy context.
• Strong Python and SQL proficiency.
• First-principles thinking with dataset/feature needs.
• Experience deploying production data pipelines.

Responsibilities

• Create new features for models and agents and expand predictive surface in data lake.
• Improve existing models via feature engineering for income/wealth, home buyer/seller models.
• Build data lake pipelines handling terabytes of data.
• Develop feature pipelines for production-scale reliability (70/30 DS/DE).
• Write validations and guardrails to ensure agent-consumable outputs.

Skills

Python

SQL

Data Engineering

Machine Learning

Tools

Dagster

dbt

Spark

Iceberg

Trino

AWS Glue

Job description

Stealth Startup in New York seeks a Data Scientist to build models and features powering our consumer graph and the agents that run on top of it. You own the path from raw data to a feature or model that an agent can call reliably at scale, and your work forms the foundation for other systems as we grow.

This role deploys constantly to production; you will own end-to-end development from data to production features, shaping a robust data lake, and ensuring outputs are ready for Minerva Agents