<p>The mission of the Autobidder team is to accelerate the world's transition to sustainable energy by maximizing the value of storage and renewable assets. We achieve this by building state-of-the-art software products for monetizing front-of-the-meter and behind-the-meter energy storage systems. Our flagship product, Autobidder, is an end-to-endautomation suite forwholesale electricity market participation of grid-connected batteries and renewable resources that maximizes revenues by optimally bidding in all available revenue streams in these markets. We are a multidisciplinary algorithmic trading team with expertise in machine learning, numerical optimization, software engineering, distributed systems, electricity markets, and trading. We have a proven track record of operating storage assets and delivering high revenues in both utility-scale and Virtual Power Plant (VPP) settings. Our products are contracted to manage over7GWh of energy storage worldwide and have returned over $420 million in trading profits, and we're slated for rapid growth on the horizon.</p> <p>As a Senior Machine Learning Engineer, you will develop forecasting algorithms for Autobidder. You will research, prototype, evaluate and productionize new forecasts forelectricity pricesand other relevant market outcomes. You will ensure thatforecasting improvementstranslate into trading revenue gains for our assets. Your work will be critical in maintaining best in best-in-class performance of Autobidder. You will own production systems and be responsible for their performance,reliability and availability. Your work will help proliferate the building of battery storage and renewable projects around the globe.</p> <ul> <li>ForecastDevelopment and Deployment:Deliver various types of electricity market-related forecasts (energy and ancillary service prices, load, regulation throughput, reserve deployments, etc.) for use in downstream algorithms </li><li>Research and Innovation:Conduct creative research to identify new machine learning approaches that improve metrics and incorporate these into our platform </li><li>Data Integration:Identify and integrate new data sources to enhance model performance while ensuring scalability and reliability of data pipelines </li><li>Production Systems:Contribute to design and development of our internal forecasting platform that supports the ML development lifecycle and hosting of the models in production </li><li>Domain Expertise:Become an expert in electricity price formation and market dynamics </li><li>Cross-Functional Collaboration:Work with optimization engineers, traders, market analysts, and software engineers to ensure forecasts drive end-to-end value </li><li>Proficiency in Python with at least 4years of experience in software development, familiarity with software developmentpractices, writing production-quality code, and agile development </li><li>Theoretical and applied experience with a variety of forecasting algorithms and approaches, including statistical, regression, and deep learning algorithms. Expert understanding of each approach, as well as demonstrated ability to select the right model depending on the application </li><li>Demonstrated experience in developing, deploying, and maintaining ML models in production for time series forecasting applications </li><li>Experience with cloud-hosted systems and related tooling, including compute services, container orchestration, and database and data warehouse platforms </li><li>Expertise with relevant Python libraries such as pandas, numpy, xgboost, lightgbm, pytorch, sklearn, plotly, seaborn, streamlit, and more </li><li>Intrinsic motivation and passion for learning, collaboration, and working in the clean energy space </li><li>Prefer academic training in machine learning, statistics and related mathematics </li><li>Prefer domain expertise in forecasting, analysis, or trading in electricity markets (e.g., ISOs like ERCOT, CAISO, PJM, AEMO, UK National Grid) </li><li>Prefer experience working with production cost models, network modeling tools, and weather models </li><li>Prefer familiarity with forecastinglibraries such as Nixtla, Pytorch-Forecasting, or Darts </li></ul>