Tesla’s Opticaster team is building applied machine learning that helps optimize when batteries are charged and discharged to maximize value for customers and the grid. This role focuses on productionizing forecasting and decision-support models for load and solar, strengthening evaluation and monitoring, and delivering robust ML that can operate at fleet scale in Tesla’s energy ecosystem.
Location: Palo Alto, CA (onsite)
Compensation: USD 140,000 - 312,000 per yearly + cash and stock awards + benefits
What you’ll work on
- Develop, improve, and productionize machine learning components in Opticaster, including time-series forecasting (for example load and solar) and additional models that inform battery dispatch
- Apply ML and system intelligence models to improve Opticaster’s energy decisions in production
- Implement model and algorithm updates in the Opticaster codebase using production Python, with tests and coordination for safe rollout plus firmware and release alignment
- Build and maintain evaluation pipelines including offline metrics, simulation, benchmarking, and regression detection to quantify ML impact and catch regressions before release
- Diagnose field and simulation issues by distinguishing model or data problems from interface and integration problems
- Improve observability for production ML with monitoring, alerting, and tooling to clarify model behavior across the fleet
- Identify and remove performance bottlenecks across ML pipelines, including CPU, memory, latency, and constrained on-device/runtime paths
- Collaborate with algorithm, software, firmware, and product engineers to integrate ML into Tesla’s residential energy ecosystem
What you bring
- Degree in Computer Science, Engineering, Statistics, or a related technical field (or equivalent experience)
- Strong Python proficiency and the ability to contribute productively in a large existing codebase
- Experience shipping applied machine learning into production systems across training, evaluation, deployment, and ongoing operation, with time-series forecasting a strong plus
- Experience owning production software end-to-end, with focus on correctness, performance, and maintainability
- Experience validating model changes using offline metrics, simulation, or regression-style evaluation against real data
- Experience with cloud and data technologies such as AWS, Spark, Airflow/Argo (or equivalent orchestration), Docker/Kubernetes, and CI/CD
- Excellent communication skills and experience collaborating across algorithm, software, firmware, and product partners
- Rust experience is a plus
- Experience with energy systems, battery storage, or similar real-world control systems is a plus
Technologies
- Python, AWS, Spark, Airflow/Argo, Docker, Kubernetes, CI/CD
Benefits
- Medical plans with options and $0 payroll deduction
- Family-building, fertility, adoption and surrogacy benefits
- Dental (including orthodontic coverage) and vision plans with options and $0 paycheck contribution
- Company paid HSA contribution when enrolled in the High-Deductible medical plan with HSA
- Healthcare and Dependent Care Flexible Spending Accounts (FSA)
- 401(k) with employer match, Employee Stock Purchase Plans, and other financial benefits
- Company paid Basic Life, AD&D
- Short-term and long-term disability insurance (90 day waiting period)
- Employee Assistance Program
- Sick and Vacation time (Flex time for salary positions, Accrued hours for Hourly positions), and Paid Holidays
- Back-up childcare and parenting support resources
- Voluntary benefits including critical illness, hospital indemnity, accident insurance, theft & legal services, and pet insurance
- Weight Loss and Tobacco Cessation Programs
- Tesla Babies program
- Commuter benefits, employee discounts and perks program
- Earned Wage Access: real-time pay access paid daily (subject to eligibility and schedule for roles below Sr. Managers levels)
What to expect
Opticaster’s mission is to accelerate the world’s transition to sustainable energy by optimizing how batteries are charged and discharged to maximize value for customers and the grid. Opticaster’s algorithms determine best times to store and use energy by considering electricity prices, solar generation, and grid conditions, supporting Tesla’s energy products including Megapacks, Powerwalls, Virtual Power Plants, and microgrids.
With a global fleet of over 500,000 residential systems, the software must run reliably at scale. Opticaster also supports grid stability through programs such as demand response and integrates with Autobidder to participate in electricity markets. As a Machine Learning Engineer on Opticaster, you will own applied ML models including time-series forecasting for load and solar, improve evaluation and monitoring, and ship production-grade models so they scale across the full fleet.