Senior/Staff Data Scientist (Recommendations)

San Francisco, USA
Engineering – Data Science
Employee - FT is searching for a Senior/Staff Data Scientist to help us build Intelligent content understanding, personalization and recommendation services within our scalable machine learning platform, that leverages adaptive exploration, text-based embeddings, high-level of automation and contextual bayesian bandits.

We’re a social impact business (a public benefit company), and the largest tech platform focused on civic action in the world with 80m monthly users, 50,000 campaigns launched on the site every month, 150 staff, and a new revenue model that has grown by 500% in 2 years. We’re growing quickly, and our users win campaigns for change once every hour. From strengthening hate crime legislation in South Africa; fighting corruption in Indonesia, Italy, and Brazil; to fighting violence against women in India.

We are looking for a Senior/Staff Data Scientist who is great at prototyping, developing and tuning custom machine learning models on big data using a distributed computing framework, designing experiments & developing embeddings from textual data for modeling semantic meaning and transfer learning at scale and has a passion for expanding our platform to mobilize hundreds of millions of people to take deeper civic action.

You will be based out of our San Francisco headquarters and report to our Head of Machine Learning and AI.  As a key member of our Data Intelligence pack, you’ll help us enable adaptive personalized user experiences on our site, recommend the best petitions to our altruistic supporters & enable staff-level support for petition starters beyond human scale. 

You’re a perfect fit for this role if your superpower is creating signals from a combination of data sources, a critical eye for introspective data analysis and experiment design, and customizing machine learning models towards solving a unique petition recommendation and inventory optimization problem. 

A Senior Data Scientist at Change is someone who can work effectively and independently, manage their own priorities and make appropriate progress with minimal supervision. Typically, Senior Data Scientists have 3-5 years of relevant industry experience as well as a mastery of one skill, such as developing machine learning models using a distributed event interaction data, designing new online experiments and novel signals on live time series data, or inventing processes and hooks for data collection and enrichment, etc.

A Staff Data Scientist at Change is not only able to work effectively and efficiently at scale, but they also set direction and priorities for a small number of adjacent data scientists and machine learning engineers. 

When we get busy, it’s likely that we’re making headline news somewhere. It is a distinct pleasure to know we are providing a personalized experience that is empowering people all over the world. Our team takes great pride in using AI powers for good.

Key responsibilities:

    • Deep analysis, and deriving insights from our rich user interaction and petition data 
    • Designing and owning experiment shots for tuning our live recommendation pipelines 
    • Defining specs, prototyping and developing ML models for our live pipelines, that improve the engagement 
    • Designing processes for collecting, enriching and inferring data on our users and our petitions
    • Designing and developing content embeddings and additional context signals, as well as creating labeled datasets for ML modeling 
    • Participate in design discussions to improve our existing machine learning frameworks and recommendation pipelines

The most important capabilities for the role are:

    • Experience with big data interactive analysis in Zeppelin/Spark notebooks 
    • Good coding skills using one language of choice (python or Scala) and excellent SQL knowledge 
    • Strong Statistics and Machine Learning foundations
    • 3+ years experience with productizing and deploying machine learning pipelines on industry tasks and in production environments, using a large scale distributed computation framework such as Spark (pyspark or Scala) and various ML and NLP libraries
    • Business oriented hypothesis testing and experiments design, a creative mindset for designing loops for data collection and signal generation

Additional capabilities we’ll consider:

    • Experience creating embeddings from text and combined data 
    • Experience with building recommendations for B2C line of products
    • Speaking or understanding multiple languages (ES, RU, FR, etc)
    • A good communicator with a pragmatic attitude for meeting business needs
Interested? Great! Here's what you should know:
This is a full-time role based in San Francisco. Our team is high impact, low ego, and has an amazing culture to be part of.

We are accepting applications until 30th of May, 2020

We especially encourage applicants of different backgrounds, cultures, genders, experiences, abilities and perspectives to apply. We’re actively working to increase the diversity of experience and perspectives on our team and are looking for someone who can help continue to lead that process. is committed to being a diverse and inclusive workplace. All qualified applicants will receive consideration for employment without regard to race, color, national origin, religion, sexual orientation, gender, gender identity, age, physical disability, or length of time spent unemployed.