Job: Data/ML Engineer

The company’s system of focus is the electric grid: they are building the ‘brain’ for, arguably, humanity’s most complex invention to date, enabling billions of individual components like electric vehicles, solar farms, and demand response to operate effectively, and in parallel. Their brain will inform everything from grid operations to buildout and is paramount to entering the next age of humanity: the Electric Age, when we as a species have the abundant energy resources required to continue our exponential progress, yet still live in symbiosis with our planet.

The company’s software is a sophisticated hybrid of machine learning and compute-efficient physical models. They use their software to predict electricity prices both for proprietary trading and to advise their clients with renewable generation on how to most profitably manage their assets; So far in 2022, trading capital informed by their software has grown +50% year to date.

The team comes from Harvard, MIT, Google, MORSE, Wayfair, USC, ClimateConnect and Wall Street, and its founders were Y Combinator S19 alums.

WORK CULTURE

At our client’s company, they believe a positive workplace environment is critical to their success. The following values are embedded in their company’s core principles:

Humility: Understanding we all can learn and improve is vital to a growth mindset

Transparency: They can only work together to solve problems when they open up their work to others

Candor: Giving and receiving feedback is a radical act of caring and ensures they can reach their potential

Inclusivity: They are strongest when all individuals and perspectives feel able to speak their mind, share ideas, and own their future

WHAT YOU’LL DO

You will be collaborating closely with our client’s software and data science teams to implement best data management practices for their ML pipeline – a pipeline forecasting more than a billion data points annually for the electric grid. Responsibilities of this role include:

• Iterating on their existing data pipelines for added reliability and improved data integrity
• Managing their ML experiment outputs for better tracking, visibility, and auditing
• Optimizing data formats and storage techniques to improve ML model performance
• Implementing complex data transformations for use within their data pipeline

REQUIREMENTS

The ideal candidate must be highly motivated and work well in a collaborative environment without direct mentorship. Our client’s team is small, with only 5 members across both software and data science teams combined – this candidate must be able to work independently and take full ownership of their work. The following skills are desired for this role:

• A knowledge of the tradeoffs between various data stores and data pipelining tools
• Experience implementing proper data management techniques for large ML datasets
• Familiarity working in Python
• Experience working in cloud ecosystems, preferably GCP
• Clear communication – must be able to understand data science pain points and translate them into clear actionable tasks
• An ability to independently research and architect one’s own solutions
• A willingness to implement, manage, and troubleshoot solutions from conception through to post-deployment
• Clear documentation – must clearly document one’s work and be able to explain or teach it to the team
• A strong interest in working for a company that fights for environmental sustainability

NICE-TO-HAVES:

Upcoming projects may involve solving mathematically complex and compute intensive constraint optimization problems. While certainly not a requirement, experience solving constraint optimization problems in compute efficient ways would be a huge plus!

WHO YOU’LL WORK WITH

You will work on the software development team, interfacing regularly with our client’s CTO, head of data science, and senior employees on both the software and data science teams.