Data Scientist

Key Skills

Algorithms, AWS, Data Architecture, Data Modeling, Data science techniques, Data Visualization, Machine learning techniques, Python Programming, Scikit-learn, Signal processing, SQL

Job Description

We aim to establish the SPAN Panel as the center of home energy and the backbone of the renewable distributed grid. Analytics and ML are essential tools to develop features for the smart, green, energy-efficient home of the future. SPAN’s unique ability to monitor and control individual circuits opens up a new avenue for proactive whole-home management and equipment failure detection. As a Data Scientist, you will leverage your deep understanding of ML, modeling, and statistics to solve problems including anomaly detection, event prediction and context understanding with the goal to optimally manage whole-home energy consumption, deliver meaningful insights to the customer, and notify them about a potential failure of equipment or hazards in their home. You’ll be involved through the entire development process, from the acquisition of all additional third-party data, the initial design to remote monitoring in the field.

Responsibilities

Lead the development of data products from the ground up which includes:

• Gain knowledge in the relevant domain (e.g.appliance signatures, failure modes, load disaggregation)

• Feature engineering (including embedded implementation for dimensionality reduction)

• Use your experience with different machine learning frameworks to identify suitable tools for integration in SPAN’s software platform

• Proactively identify opportunities within SPAN that can benefit from data science analysis

• Use fleet data to monitor algorithms in the field

Note: We’re a startup, so while this list is broad, it’s still just a start; you’ll end up wearing many hats during your time at SPAN

About You

Required Qualifications

• Master’s degree or higher in Computer Science, Mathematics, Engineering, or a closely related field

• 7+ years' of professional experience with developing, implementing, and analyzing algorithms in a production environment

• Deep experience with and understanding of machine learning systems, which includes familiarity with topics such as feature extraction from high-frequency signals, noisy labels, ML for physical processes, model explainability, model compression and edge inference

• Experience with high-frequency time series modeling

• Advanced Python skills, as well as familiarity with pandas and scikit-learn

• Software design experience and ability to write clean, maintainable, and shippable production code

• Experience working within cloud computing environments such as AWS

• Experience working with SQL and data visualization tools

• Extensive data modeling and data architecture skills

• Strong communication and interpersonal skills

• Ability to understand and explain complex problems simply and effectively

Bonus Qualifications

• Experience with the Energy industry

• Experience with building IoT and/or hardware products

• Experience with Flink and/or Apache Flink

• Experience with digital signal processing as applied to feature extraction and processing

• Understanding of electrical systems and residential loads

The U.S. base salary range for this position is $150,000- $200,000 plus benefits, equity and variable compensation for Sales-related roles. This range represents SPAN’s good faith estimate of competitively-priced salary for the role based on national, real-time industry data from companies of a similar growth stage. This range reflects minimum and maximum new hire salaries for the role across US locations. Within the range, individual pay is determined by location and individual factors including relevant skills, experience and education or training. This range correlates to the relative level of the candidate we believe we need for the role and may require an adjustment for candidates of a different level.

Your recruiter can share more about the specific salary range for the location this role is based during the hiring process.