Data Scientist (Data Insights)
Full-time
Bellevue, WA
Job Description
Get to know the team:
The Data Insights team, also known as the Business Data Platform, owns the online real-time single source of truth for all user data at Grab.
Get to know the Role:
- Develop a deep behavioral understanding and intuition of our passengers and drivers
- Manage and own the entire end-to-end lifecycle of designing models, working with Engineering for implementation, to maintenance and enforcement
- Generate multivariate statistical models to identify latent factors, preventive and preemptive capabilities that the framework requires
- Interface with business & operation teams to formulate solutions & product changes informed by your findings
- Work independently or in a team to solve complex problem statements
The day-to-day activities:
- Translate these intuitions into actionable, creative insights that produces heuristic or classification models to identify and take down those who violate our Terms of Services
- Test and validate these insights via rapid experimentation and deployment
- Develop creative algorithms by employing machine learning, and data mining techniques
- Contribute to team’s innovation and IP creation
- Build, validate, test, and deploy machine learning models (e.g. predictive, forecasting, clustering) using proven and experimental techniques. Deploy an online learning model where applicable
- Define hypotheses, develop and execute necessary tests, experiments, and analyses to prove or disprove them
- Translate data speak to human speak by effectively conceptualizing analysis to team members and business stakeholders
The must haves:
- Proficient in RDBMS such as PostgresQL or MySQL; and statistical programming in languages like R, Python, Java, C++ or SAS
- Experience in ETL, feature selections, modeling, model validation and conducting data analyses using R, SQL, Python or any JVM languages
- Deep understanding and implementation experience of predictive modeling algorithms such as logistic regression, neural networks, forward propagation, decision trees and heuristic models, with familiarity dealing with trade offs between model performance and business needs
- Experience in interfacing with other teams and departments to deliver impact solutions for organisation
- Self-motivated, independent learner, and enjoy sharing knowledge with team members
- Detail-oriented and efficient time manager in a dynamic and fast-paced working environment
Really nice to haves:
- Experience in geospatial databases or graph databases
- Recent programming experience in a production environment
- Experience in Scala or PySpark on distributed systems
- Interest in working with MapReduce technologies (such as Hadoop / Spark)
- Familiarity with Python Scikit Learn, Panda or Spark ML/Mllib is a plus
