Battery Optimization Data Scientist (Hybrid)

Rodan Energy; Mississauga; Hybrid; CAD 110,000 - 130,000; Full time

Benefits offered by this job

Hybrid: 3 days in Mississauga office

Profit sharing

Health benefits

RRSP with employer matching

Job summary

Rodan Energy is seeking a data-driven optimization engineer to build and own battery and price-responsive load (PRL) optimization models. You will backtest against historical data, track experiments with MLflow, and partner with forecasting scientists to incorporate forecasts into models.

You will work within a growing data platform, collaborating with data engineering and applied researchers to ensure data quality and robust deployments across multiple energy markets.

Qualifications

• Degree in Operations Research, Applied Math, Statistics, or related field (MS/PhD preferred).
• 3+ years building optimization models in production or research.
• Experience backtesting models and tracking results (MLflow or equivalent).
• Strong Python and SQL for large time-series data processing.
• Ability to translate real-world problems into mathematical models.
• Ability to work independently in early-stage environment.

Responsibilities

• Build and own optimization models for battery and PRL performance against DA/RT signals.
• Lead battery optimization project after initial shadow period.
• Backtest models against historical data before deployment.
• Track experiments and backtest results in MLflow for comparability.
• Collaborate with forecasting data scientists to input forecasts into models.
• Coordinate with Data Engineering to ensure data quality for models.
• Support expansion of optimization across additional markets (IESO, AESO, PJM, NYISO, MISO, ERCOT).

Skills

Optimization models

Python

SQL

Backtesting

Independent work

Education

MSc or PhD in OR/Applied Math

Bachelor in quantitative field

Tools

Databricks

MLflow

Gurobi/CPLEX

Job description

Rodan Energy is seeking a data-driven optimization engineer to build and own battery and price-responsive load (PRL) optimization models. You will backtest against historical data, track experiments with MLflow, and partner with forecasting scientists to incorporate forecasts into models.

You will work within a growing data platform, collaborating with data engineering and applied researchers to ensure data quality and robust deployments across multiple energy markets.