Thorn is a non-profit focused on building technology to defend children from sexual abuse. Working at Thorn gives you the opportunity to apply your skills, expertise, and passions to directly impact the lives of vulnerable and abused children. Our staff solves dynamic, quickly evolving problems with our network of partners from tech companies, NGOs, and law enforcement agencies. If you are able to bring clarity to complexity and lightness to heavy problems, you could be a great fit for our team.

Earlier this year, our CEO, Julie Cordua, took the stage at TED and shared our audacious goal of eliminating child sexual abuse material from the internet. A key aspect of our work is partnering with the National Center for Missing & Exploited Children and building technology to optimize the broader ecosystem combating online child sexual abuse.

About the Role:

As Data Scientist, you will join our small but mighty organization at the early stage of this product, and you will work together with our team to implement and ship a world-class product. You will uncover valuable insights, adding intelligence to our existing and future products. The work you will do will be a combination of finding quick wins and developing longer term research. You will collaborate closely with Engineering and Product to identify insights and models most valuable to research and implement. You will be responsible for acquiring data, crafting and performing analytical experiments in a disciplined manner, evaluating and iterating on results, and discussing results with your team. When you and the team conclude that the model or insight is ready to be shipped, you will partner with members of the Engineering team to simplify, architect, and implement an infrastructure for continuous deployment.

What You’ll Do:

• Research and develop statistical modeling for data analysis.
• Collaborate with team members to drive understanding of product needs and devise possible solutions.
• Discuss results and ideas with key partners.
• Implement new statistical, or other mathematical methodologies, as needed for specific models or analysis.
• Work with Engineering team members on deploying insights and models and continuous model training and deployment.
• Keep up-to-date with the newest developments in data science and machine learning.

Skills We’re Seeking:

• You have have experience in designing and building machine learning models for production.
• You have a background in data science and statistical analysis.
• You have experience with natural language processing, computer vision and deep learning.
• You have an ability and interest in learning new technologies quickly.
• You have a passion for machine learning and an aptitude to work in a collaborative environment, can demonstrate empathy and strong advocacy for our users, while balancing the vision and constraints of engineering.
• You communicate clearly, efficiently, and thoughtfully. We’re a highly-distributed team, so written communication is crucial.

Technologies We Use:

You should have non-trivial experience with at least a few of these, but we’re open to teaching folks that have the desire and ability to learn the rest.

• Python
• Pandas
• Scikit Learn
• NLTK, Gensim
• Tensorflow or Keras or PyTorch etc.
• Jupyter

Thorn is a strong and flexible team because of the diverse backgrounds of our staff. This includes professional background, subject matter expertise, culture, race/ethnicity, sexual orientation, gender identity, and expression, language, hobbies, etc. We strongly encourage women, minorities, and people from underrepresented backgrounds to apply. Your skills are needed here.