Data Scientist, Forecasting and Energy Storage System Optimization

About Stem - Driven by human and artificial intelligence – Stem is unlocking energy intelligence.

Stem is a global leader reimagining technology to support the energy transition. Turning complexity into clarity, and potential into performance.
We help asset owners, operators and stakeholders benefit from the full value of their energy portfolio by enabling the intelligent development, deployment, and operation of clean energy assets. Our integrated software suite, PowerTrack, is the industry standard and best-in-class for asset monitoring, supported by professional and managed services, under one roof. Meant to tackle challenges as seamlessly as possible, Stem shows the information needed clearly and accurately and helps harness raw data to inform actionable insight. With global projects managed in 55 countries – from Germany to Japan and across North America – customers have relied on Stem for nearly 20 years to maximize the value of their clean energy projects.

Stem’s culture embodies diversity & inclusion beyond the traditional facets of gender, ethnicity, age, disabilities, and sexual orientation to include experience, personality, communication, workstyles, and more. At our core, Stem is at the momentous intersection of clean energy and software technology where diverse ideas, experiences, and professional skills converge to make the inclusive culture we have today. Together, we are turning old school thoughts about software and energy into progressive, collaborative, and innovative solutions. By joining our team, you will be collaborating with data scientists, energy experts, skilled salespeople, thought-leading executives and more from a range of backgrounds. This intersection of ideas, beliefs, and skills is what makes us unique enough to lead the world’s largest network of digitally connected energy storage systems.

What we are looking for/Role Overview:

Stem is seeking a highly skilled and motivated Data Scientist to join our team. This role is focused on leveraging advanced data analysis, machine learning, and statistical modeling expertise to contribute to the development and optimization of our AI-driven clean energy platform in PowerTrack, Stem’s core suite of products. If you are a problem solver, critical thinker, and team player with a passion for using data to drive impact in the clean energy sector, we encourage you to apply.

Key Responsibilities:

• Develop, implement, and deploy machine learning models and statistical analyses to optimize energy storage and solar asset performance across Stem's portfolio
• Design and build data pipelines to extract, transform, and analyze large-scale datasets from energy systems
• Collaborate with software engineering, product management, and energy experts to integrate data-driven solutions into PowerTrack platforms
• Create data visualizations, dashboards, and reports to communicate insights and recommendations to stakeholders
• Conduct exploratory data analysis to identify trends, patterns, and opportunities for improving system performance and business outcomes

Required Qualifications:

• Minimum of 1-3 years in data science, analytics, machine learning, or related field
• Bachelor's degree in Data Science, Statistics, Computer Science, Mathematics, Engineering, or related field, or equivalent experience
• Proficiency in Python and data science libraries (pandas, numpy, scikit-learn, TensorFlow or PyTorch)
• Familiarity with optimization libraries (e.g. CVXPY) and experience formulating or interpreting constrained optimization problems
• Strong SQL skills and experience working with large datasets using SQL or SQL-like query languages.
• Comfortable using modern AI coding assistants (Cursor, Claude Code, GitHub Copilot, etc.) to accelerate development
• Experience writing well documented, well tested, and maintainable code
• Version control with Git and experience using GitHub, GitLab, or Bitbucket
• Experience prototyping analyses in Jupyter notebooks and building lightweight data applications to explore and communicate insights, using tools such as Matplotlib, Seaborn, Plotly, and frameworks like Streamlit or Dash.
• Strong analytical and problem-solving skills with expertise in statistical methods and machine learning algorithms
• Excellent communication and presentation abilities with capacity to translate complex technical findings for diverse audiences

Preferred Qualifications:

• Experience with cloud platforms (AWS, Azure, GCP) and distributed computing frameworks
• Familiarity with microservices architecture and containerization (Docker, REST APIs) 
• Basic understanding of kubernetes, deployment pipelines, and monitoring tools (Grafana, Kibana) 
• Familiarity with