About Us

Local Energy is building software for the next generation of industrial energy systems.

We help industrial sites and energy infrastructure operators recover waste heat, optimize energy flows, reduce peak demand, and operate complex energy systems more intelligently. Decarbonization isn’t just our goal, it’s our core mission. Through AI-powered simulation and optimization tools, we enable the design of smart local grids and unlock dynamic energy markets. Our platform helps reduce emissions, drive efficiency, and create shared economic value, all while building more sustainable, resilient energy systems.

We are supported in part by Mila, a world-leading AI research institute, to build innovative solutions for the climate crisis focused on industrial local energy networks. We’re early-stage, funded, and growing fast and now we’re building out our engineering team from the ground up.

The Role

We are looking for an ML Engineer who can build applied forecasting and predictive modelling systems for industrial energy applications.

You will work on real time-series problems involving energy demand, load profiles, renewable production, operational signals, and other variables that influence how energy systems are designed and operated.

The role is intentionally practical and high-ownership. You should enjoy working with messy data, testing different modelling approaches, making trade-offs, and delivering models that are useful inside real product and client contexts.

You should be excited by questions like:

• How do we forecast the evolution of complex energy demand over time?
• How do we make predictive outputs usable inside planning, simulation and operational workflows?
• How do we connect forecasting, optimization, and future control systems in a practical way?
• How do we build models that are robust enough for physical infrastructure, not just benchmark datasets?

What You’ll Do

• Build predictive components that estimate the evolution of key system variables over time, including energy demand, load profiles, renewable production, and other operational drivers.
• Develop end-to-end modeling pipelines, from raw data preparation and feature engineering to model evaluation and practical delivery.
• Compare and apply methods ranging from statistical forecasting approaches to modern sequence models and structured temporal models.
• Work with time-series data from industrial and energy systems, including imperfect, incomplete, and heterogeneous datasets.
• Integrate forecasting outputs into planning, simulation, and operational workflows so they improve decision-making rather than remaining standalone analysis.
• Collaborate with the software and product teams to make sure models are usable, maintainable, and aligned with the needs of the platform.