Since the Paris Agreement, global banks have poured a staggering $6.9t into the fossil fuel industry. At Bank.Green, our mission is to lower this vast carbon footprint via technology and consumer action. We empower bank customers with the tools and insights they need to influence their banks towards sustainable lending, or switch to greener alternatives. To date, our bank-checking tool has been used over 500,000 times by bank customers worldwide, while we have shifted a at least $35,000,000 towards banks who are financing a greener future.
Through transparency, engagement, and innovation, we aim to redefine the role of banks in the fight against climate change.
Bank.Green is seeking a data scientist to help anayze bank sustainability policies and fossil fuel financing. This work involves using LLMs, knowledge graphs, SQL joins, and python pandas to infer row similarity across multiple datasets, generate filter statements, and collect data on fossil fuel companies.
One of our volunteers is a professor of data science and is producing some interesting and exciting results. There is mentorship involved in this role. There are also opportunities to publish your work and results on the Bank.Green blog. If you were interested in publishing in a journal we would also be happy to support that.
You do not need to have previous experience as a data scientist to join this team but you do need to have a firm grasp of SQL and python and the ability to learn about LLMs and graph databases.
This role is unpaid and volunteer-based. We are seeking a commitment of 10-20 hours per week. We are looking for somebody to come on long-term, for at least a 6 month commitment.
Use LLMs to extract and categorize pledges in bank sustainability policies
Convert pledges into SQL query statements
Prepare joins across multiple datasources with similar rows.
In some cases, unique identifiers are not available. In other cases something represented in one row in a dataset can be represented in two rows in another.
Develop tooling to enrich our fossil fuel company dataset
Attend data meetings and discussions
Experience in technical development
Proficiency in SQL
Proficiency in Python
Familiarity with Python Pandas
Interest in working asynchronously with colleagues in different time zones - through Slack, MS Teams, or similar
Good communication and teamwork abilities
Passion for sustainability and environmental advocacy