Machine Learning Engineer

Role Overview

Camus is seeking an individual contributor Machine Learning Engineer to own and advance the platform’s forecasting and predictive modeling capabilities. You’ll take models from exploratory analysis and design through production deployment and monitoring, working with engineering and external stakeholders to turn messy signals into reliable analytics.

Responsibilities

• Design, train, and evaluate forecasting and other time-series predictive ML models
• Perform exploratory data analysis, feature engineering, and statistical modeling across large structured/unstructured datasets
• Partner with Engineering to define ML infrastructure requirements and deploy/integrate models into operational workflows and decision-support tools
• Work cross-functionally to define ML problem statements and translate business objectives into ML solutions
• Communicate model performance, uncertainty, and limitations to technical and non-technical stakeholders
• Promote ML best practices including reproducibility, versioning, and testing

Requirements

• PhD + 3+ years, Master’s + 5+ years, or Bachelor’s + 8+ years in ML, Statistics, CS, Applied Math, or a related quantitative field
• Proven track record delivering ML models into production
• Experience with time-series forecasting, including:
  • Classical methods (e.g., ARIMA)
  • Modern ML approaches (e.g., gradient boosting, temporal neural networks)
• Strong proficiency in Python and core ML/data science libraries (PyTorch, scikit-learn, statsmodels, pandas, etc.)
• Experience with probabilistic forecasting, uncertainty quantification, and backtesting
• Ability to convert ambiguous business problems into well-scoped ML projects
• Ability to operate with autonomy in a small, fast-moving team while maintaining production engineering discipline

Nice to Have

• Experience in the energy sector, such as load forecasting, renewable generation prediction, price modeling, or grid operations