Job Description
Go’s Data Science team is looking for an exceptional Senior Data Scientist to join our fully distributed team.
Team Go was started with the simple premise that our real-world connections matter, that people matter. We are building a very different kind of social app, one that helps people get together to create memorable experiences in real life.
We believe in a world where social technology unites us and makes us happier. Our team is on a mission to fix social isolation and bring people together to do things they love with the people they love.
As Senior Data Scientist on the team, you will have an outsized impact on our applied machine learning research, internal analytics, and production systems. You will work with other data scientists, data engineers, and cross-functionally across the org to build prototype models, iterate upon them, launch them, and monitor their performance in production.
For this role, we are looking for a generalist with a natural language processing background. You will be primarily working on our text categorization models using tools like Apache Spark, Spark NLP, and Tensorflow, but you will also contribute to several additional projects in our pipeline.
Our Data team is a deliverables-based organization. We believe that you will do your best work if you have the autonomy to define when and from where you work. We also believe that your performance should be judged by parameters that we agree on collaboratively. But this job will not be easy––we are looking for a candidate who likes to create innovative applied machine learning solutions to hard problems at scale.
Key Responsibilities
- Write clean, easy-to-read Python/Pyspark code, with plenty of comments for your peers and your future self.
- Develop and iterate upon our text categorization models and production systems.
- Build dashboards and assist with internal analytics needs.
- Assist Data Engineering with building and iterating upon the pipelines that feed your models.
- Craft internal memos to keep everyone up to date on the status and performance of models and systems.
- Mentor junior data scientists on staff
- Propose new projects to the Data Science leadership team
- Contribute to the project planning process by estimating tasks and deliverables.
Skills and Qualifications
- You have a BS or higher in Computer Science, Mathematics, Statistics, Economics, or another quantitative field.
- You have at least three years of experience working on applied machine learning systems in production cloud environments (AWS, Google Cloud, etc.)
- You have experience along the entire machine learning product lifecycle, from initial data ingest and data prep, through to modeling and creating REST API endpoints or managing batch inference workloads, and subsequently monitoring model performance and evaluating drift.
- You are technically competent with the Python data science ecosystem (Pandas, Numpy, SciPy, Sci-kit, Jupyter);Apache Spark and associated frameworks (Spark NLP, Spark Streaming, Spark MLlib);and Tensorflow/Keras.
- You have production experience with messy natural language systems. You know all about tokenization, feature vectorization, word embedding, and training language models. You have seen algorithms fail due to bad input data.
- You are a skilled written communicator. Our team is 100% remote and writing is our primary means of communication. You communicate complex technical topics clearly and in an approachable way.
- You enjoy collaboration and knowledge sharing. You appreciate our team’s values of humility and you are eager to collaborate with teammates with any level of statistical or engineering knowledge.
- You have experience documenting projects and processes with tools like Jira and Confluence.
- You understand that perfect is the enemy of good, and you like to stay away from over-engineered solutions. You like to find simple solutions that work, iterating upon them as needed.
Stack Overflow