Green Energy Pal, a startup founded in 2023, is looking for employees to expand its data science team. We are looking for data scientists with a focus on time series (signals) of different seniority who would join our team in the development of new and innovative solutions in the field of electricity consumption monitoring.

About us

We are a young startup operating at the intersection of 3 domains: energy, data science and IT. We are developing our own solution for monitoring the consumption and production of electricity in real time – Enpulse. Enpulse consists of measuring hardware that is installed in the main distribution cabinet and software that deals with data storage and processing. Using this data, we develop cutting-edge machine learning algorithms for the detection of individual devices from the total consumption curve (so-called NILM, non-intrusive load monitoring).

In short, we want to be the first in the world to make it possible to identify the consumption of individual devices, such as washing machines, air conditioners, etc., from low-frequency measurements (such as smart meters) of total electricity consumption at one measuring point (e.g. in your apartment). This increases the possibility of saving energy, identifies malfunctions, detects the possibility of fire, informs the household that the oven was left on after they left the house, etc. Our target clients are mainly various facilities, hotels, property owners, etc.

Members of the founding team of Green Energy Pal are doctoral students and doctors of science who at one point worked together at the Institute for High Voltage and Energy at FER. In the meantime, our team has expanded with 2 full-stack developers, and we currently have 5 members.

About work

The goal of the work is to create algorithms that will allow each of our clients to know which devices are consuming how much at any given moment, without having a consumption sensor on each device. To achieve this, we collect time series of total electricity consumption using our own measuring devices and store the data on our cloud.

The job includes:

• retrieving data from our databases or via API
• data cleaning (missing values, outliers…)
• Statistical data analysis
• Digital processing of signals and searching for features that can be useful in the detection of individual devices
• Creation of prototype models (machine learning and statistical) for the detection of individual devices
• Cooperation with the IT team regarding the conversion of prototypes into deployed production models for the detection of individual devices
• Analysis of models working in production with the aim of improving the accuracy of algorithms
• If you are more experienced and of greater seniority, you will participate in choosing a modeling approach, model architecture and deciding how to do data labels

What we offer

• Opportunity to get shares in the company: Become a co-owner of Green Energy Pal and share the success with us.
• Flexible working hours: Working hours adapted to your needs.
• Flexible workplace: Work from our office in ZICER, from home or any place that suits you.
• Quality equipment: Choose the tools that suit you best for efficient work.
• Education and development: Attend conferences, courses and training to keep up with the latest technologies.

What are we looking for?

We are looking for a person who is:

• responsible in performing tasks for work in a dynamic startup environment
• proactive, creative and results-oriented
• ready to learn and gradually take on additional responsibilities as our startup and team grow
• thinking outside the box

While ideally you should be proficient in all of the areas listed below, it is sufficient that you have experience in some of these areas and are willing to learn and grow.

The ideal candidate has:

• Strong mathematical background, primarily statistics and digital signal processing
• Experience working with time series
• Background in data science/machine learning

It is not mandatory, but it is an advantage if:

• you like the startup environment
• you work with Python, primarily: Pandas, NumPy, SciPy, Scikit-learn…
• you have experience with time series forecasts (especially in energy)
• you have experience with databases

Additional notes:

• Since we do things that no one has done before, previous experience in a specific niche is not necessary, if you have a strong background in digital signal processing or data science background and a willingness to learn, apply
• If you are a student and you really like what we do, but you don’t have the necessary knowledge yet, you can apply for an internship

Type of employment:

Employment contract

Application deadline

We accept applications until December 2, 2024.

Send your CV to careers@gep.energy or come to our office in ZICER (with prior notice to careers@gep.energy so that we can tidy up the office 🙂