Software Engineer - ML Platform (Staff / Sr Staff)

Equilibrium Energy is a clean energy startup focused on reimagining the power sector through AI technology. They are seeking Staff / Sr Staff Software Engineers to develop and operationalize scalable machine learning models for forecasting and optimization, enabling both internal and external users to leverage these capabilities effectively.

Responsibilities:

• Abstract away the complexities behind the deployment and orchestration of a large number of forecasting workflows, enabling a fast model development lifecycle for our Science team
• Integrate with data and compute infrastructure to optimize resource utilization and performance
• Implement automated testing and monitoring for ML models in production
• Maintain and iterate on our model registry and experiment tracking
• Co-design frameworks that support model experimentation, hyperparameter tuning, training, and deployment
• Partner with our Data Services team to incrementally improve our feature store and tie it to the EQ ontology
• Collaborate closely with data scientists to understand new model requirements and together implement solutions that are robust, validated, and scalable
• Collaborate with the Science Platform Simulation team to incorporate forecasting into physical and portfolio asset optimizations
• Partner with our Product and Customer Delivery teams to enable external customers to perform similar tasks to our internal scientists, with minimal code divergence and following security best practices
• Stay up-to-date with the latest advancements in ML engineering and integrate best practices into the platform

Requirements:

• A commitment to clean energy and combating climate change
• Proficiency and 5+ years experience in Python software development
• Familiarity with automated build, deployment, and orchestration tools such as CI/CD, Pants, Docker, Metaflow, Argo, and Kubernetes
• Strong understanding of data pipelines, ETL, and data infrastructure
• Experience with observability tooling like Grafana, Honeycomb, and Prometheus
• Experience with common machine learning algorithms and libraries (xgboost, sklearn, pytorch, pandas, polars, pandera)
• Prior experience in operationalizing machine learning workflows
• Agility in working with cross-functional teams and adapting to new work methodologies
• Familiarity with agile practices, or a willingness to learn
• Strong communication skills for collaborating within a remote-first team that works internationally across timezones
• An advanced degree in computer science or machine learning
• Experience in time series forecasting
• Experience building tools that support data scientists
• Experience with Databricks and Spark or Dagster
• Background in the energy and power systems sector