Base Power
Algorithms Engineer
About this role
Base seeks an Algorithms Engineer to design and deploy control algorithms for a distributed battery fleet operating in wholesale energy markets. You'll develop solutions for real-time energy arbitrage, grid services, and fleet coordination while working closely with the trading desk on live market operations.
What you'll do
- Build algorithms for distributed battery fleet dispatch in wholesale energy markets (ERCOT, etc.)
- Integrate market operations algorithms with grid-service control loops for voltage regulation and peak shaving
- Participate in fleet scheduling and on-call engineering rotation
- Implement controls for aggregated battery deployments at distribution system voltages
- Analyze telemetry and performance data using SQL, Grafana, and other tools
- Drive long-term development of automated control systems across the company
What they're looking for
- Algorithmic control systems for physical systems
- Model predictive control or reinforcement learning
- Markov decision processes
- Signal processing
- SQL and data analysis tools
- Wholesale energy market operations knowledge
- Experience with Grafana or similar monitoring tools
- Strong communication and data-driven problem solving
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Base Power
Base Power develops high-power-density battery energy storage systems and related hardware for residential and commercial energy applications. The company is hiring System Design, Thermal, and Mechanical Engineers for product development, plus Supply Chain and Data Engineers to build internal platforms and infrastructure supporting distributed battery operations at scale.
View all jobs at Base PowerLikely interview questions
- Walk us through a time you deployed algorithmic control for a physical system. What metrics did you use to measure success, and how did real-world conditions differ from your models?
- Describe your experience with model predictive control, reinforcement learning, or Markov decision processes. How have you applied these to optimization problems?