Data Scientist

The role

You will architect the intelligence layer of Arch by modeling customer behavior and optimizing campaign performance. You will build scalable, production-ready machine learning systems and own the full ML lifecycle from data collection to deployment.

What you will do

• Develop and deploy predictive models to identify high-conversion leads and drive campaign targeting
• Own the full ML lifecycle from data acquisition, cleaning, and labeling to modeling, validation, and deployment
• Analyze product performance and customer usage to inform roadmap and product design
• Collaborate with the engineering team to productionize ML pipelines and integrate them into backend systems
• Work closely with leadership to build internal analytics, dashboards, and investor-facing insights
• Prototype, experiment, and iterate quickly

Required qualifications

• 3–6 years experience in data science, ML engineering, or analytics roles in fast-paced environments
• Proficiency in Python, SQL, and ML libraries (e.g., scikit-learn, XGBoost, or PyTorch)
• Familiarity with data pipelines, model evaluation, and deployment workflows
• Proven ability to work independently in ambiguous contexts with high judgment and ownership
• Experience working with business stakeholders to translate messy data into actionable insights

Nice to have

• Experience with large-scale structured data (e.g., property, utility, or energy-related datasets)
• Knowledge of marketing analytics, targeting models, or customer segmentation
• Familiarity with modern data tooling (e.g., dbt, Airflow, Dagster, DuckDB)
• Comfort with basic full-stack workflows or collaborating in a product engineering environment

About the company

Arch powers frontline industries with cutting-edge AI. They are driving energy resilience, economic strength, and long-term prosperity by bringing AI innovation to the services that need it most.