A global programmatic advertising platform with specialized healthcare expertise, fuses the science of programmatic targeting, distribution, and optimization with the art of brand engagement. The platform is powered by terabytes of impression-level data, allowing brands to efficiently engage the right audiences at scale while helping publishers increase yield through actionable insights.
Our organization has a strong history of utilizing machine learning, contextualization, and targeting to distribute advertising to the right consumers at the right time and create real connections across the internet. We are now taking that knowledge and expertise to solve challenges within healthcare in order to create better health outcomes through Radical Health Personalization.
The goals of the Data Science team:
- Optimize and validate targeting mechanisms for specific health conditions;
- Improve and optimize our proprietary contextualization and recommendation engines that handle millions of transactions per second, trillions each month;
- Improve and optimize our buying platform to ensure cost efficiency and to deliver ad campaigns within budget, target and time constraints; and
- Collaborate with internal Health experts to design and support rapid assessment, analysis, and prototyping of ideas for achievable commercialization.
What you'll be working on:
- Improve existing or develop new traffic segmentation algorithms and estimations of bid landscapes within each segment;
- Optimize real-time bidding strategies to efficiently spend ad budgets delivering campaign targets given various constraints;
- Support and enhance the existing work on health user profiling, prediction, and targeting tools;
- Improve page contextualizer technology: work with healthcare topics detection algorithms, keywords/phrases extraction, general and aspect-based sentiment analysis;
- Contribute on projects relating to patient/physician identity for cross-device tracking, profiling and targeting; and
- Support existing codebase for data integration and production support for our core models.
- 3+ years of full-time experience working as a Statistician/ Machine Learning Engineer/ Data Scientist;
- Advanced knowledge of Big Data technologies such as Hadoop, Hive/Impala and Spark;
- Advanced knowledge of Python using the numpy/scipy/pandas/sklearn stack;
- Advanced knowledge of classical ML models (logistic regression, decision trees, boosting, bagging, SVM, Bayesian methods, etc) and at least basic knowledge in different Neural Network models (CNN, RNN, auto-encoders, transformers);
- Being confident user of Unix-like systems, Dockers, git, bash; and
- MS/PhD in Applied Mathematics, Statistics, Machine Learning, Computer Science, Physics; or BS with several years of applied machine learning experience.