Lead Data Scientist (Personalization)

Get to know the role:

• Conceptualise and develop machine learning models to model Grab’s consumer preferences, behaviour and interactions, especially in the scope of ranking and recommendation

• Drive product improvements and roll-out of new features

• Drive the development and iteration of algorithms
  

The day-to-day activities:

• Deep dive into big data to conduct advanced statistical analyses

• Design and build machine learning and optimisation algorithms efficiently

• Integrate, simulate and test impact of algorithms and features on the overall system

• Develop and execute necessary analyses or A/B tests to validate models and identify improvement opportunities

• Store, retrieve and visualise results in a manner that facilitates required analyses

• Effectively conceptualize analyses to business/product stakeholders
  

The must haves:

• Minimum 4 years of relevant experience in developing ranking and recommendation algorithms

• Ph.D. or Master’s in Computer Science, Electrical/Computer Engineering, or related technical disciplines

• Strong fundamentals in Machine Learning, Optimization, and Mathematics

• Familiar with mainstream deep learning programming framework (e.g. TensorFlow)

• Familiar with deep learning algorithms (e.g. CNN/RNN/LSTM);

• Proficient in statistical programming in languages such as Python; and strong working knowledge in RDBMS such as PostgresQL or MySQL

• Excellent software development capabilities, preferably in Python/Scala/C++ with good programming style and work habits; knowledge of GoLang would be an advantage

• Self-motivated and independent learner who is willing to share knowledge with the team

• Efficient and detail oriented; good time management in a dynamic and fast-paced working environment
  

Really good to haves:

• Experience in working with food, supermarket, and e-commerce data and use cases

• Experience in open source search engines such as ElasticSearch and Solr

• Experience in parallel programming and multithreading