Doximity is the leading online medical network with over 70% of U.S. doctors as members. We have strong revenues, profits, real market traction, and we’re putting a dent in the inefficiencies of our $2.5 trillion U.S. healthcare system. After the iPhone, Doximity is the fastest adopted product by doctors of all time. Launched by Jeff Tangney in 2011; Jeff previously founded healthcare pioneer Epocrates (NASDAQ: EPOC). Our beautiful offices are located in SoMa San Francisco.

Skills & Requirements

• 4+ years of industry experience and M. S./Ph. D. in Computer Science, Engineering, Statistics, or other relevant technical field.
• 4+ years experience with various machine learning methods (classification, clustering, natural language processing, ensemble methods, deep learning) and parameters that affect their performance.
• Expert knowledge of probability and statistics (e.g., experimental design, optimization, predictive modeling).
• Experience with recommendation algorithms and strong knowledge of machine learning concepts. Solid engineering skills to build scalable solutions and help automate data processing challenges.
• Excellent problem-solving skills and ability to connect data science work to product impacts.
• Fluent in SQL and Python; experience using Apache Spark (pyspark) and working with both relational and non-relational databases.
• Familiarity with AWS, Redshift.

What you can expect

• Employ scalable statistical methods and NLP methods to develop machine learning models at scale, owning them from inception to business impact.
• Leverage knowledge of recommendation algorithms to increase user engagement through personalization of delivered content.
• Plan, engineer and measure outcomes of online experiments to help guide product development.
• Collaborate with a team of product managers, analysts, data engineers, data scientists, and other developers.
• Think creatively and outside of the box. The ability to implement and test your ideas quickly is crucial.

Technical Stack

• We historically favor Python and MySQL, but leverage other tools when appropriate for the job at hand.
• Machine learning (linear/logistic regression, ensemble-models, boosted-models, clustering, NLP, text categorization, user modeling, collaborative filtering, etc) via industry-standard packages (sklearn, nltk, -Spark ML/MLlib, GraphX/GraphFrames, NetworkX, gensim).
• A dedicated cluster is maintained to run Apache Spark for computationally intensive tasks.
• Storage solutions: Percona, Redshift, S3, HDFS, Hive, neo4j.
• Computational resources: EC2, Spark.
• Workflow management: Airflow.

Fun facts about the Data Science team

• We have access to one of the richest healthcare datasets in the world, with deep information on hundreds of thousands of healthcare professionals and their connections.
• We build code that addresses user needs, solves business problems, and streamlines internal processes.
• The members of our team bring a diverse set of technical and cultural backgrounds.
• Business decisions at Doximity are driven by our data, analyses, and insights.
• Hundreds of thousands of healthcare professionals will utilize the products you build.
• A couple times a year we run a co-op where you can pick a few people you’d like to work with and drive a specific company goal.
• We like to have fun – company outings, team lunches, and happy hours!