Lead Data Scientist (Multiple Roles and Teams)

Job description

Job Description:
Life at Grab:
At Grab, every Grabber is guided by The Grab Way, which spells out our mission, how we believe we can achieve it, and our operating principles - the 4Hs: Heart, Hunger, Honour and Humility. These principles guide and help us make decisions as we work to create economic empowerment for the people of Southeast Asia.
Data at Grab
Do you believe in the power of technology to serve millions of lives across Southeast Asia? Are you excited to augment the region's leading superapp with state-of-the-art artificial intelligence across transportation, logistics, and financial services? Are you passionate about turning big data into a force for human good? If so, we are looking for you!
About the Data Science Teams at Grab:
Our data science teams aim to improve Grab’s user experience and platform efficiency, and drive real-world impact through innovative data-driven technology. Day to day, we write codes in Python, Scala, and sometimes C++ to crunch data and implement algorithms. We take care of end-to-end flows from data analysis to deployment and evaluation in a distributed computing environment. But most of all, we love to explore and are resilient to failure.
Below are a few examples of what we are working on:
  • Recommendations: Predict the most relevant items in the user journey, such as choice of food or grocery for delivery, possible destinations for ride hailing and relevant promotions
  • ETA Prediction: Estimate the arrival time for a ride/ delivery based on real-time traffic conditions.
  • Optimization: Design algorithms to improve the performance and efficiency of Grab’s marketplace, including network optimization, combinatorial optimisation, linear and mixed integer optimisation.
  • Fraud detection: Detect fraudulent events and users with various algorithms and models including graph mining and sequential neural networks.
  • Credit scoring: Generate credit scores using high-dimensional behavioural data.
  • Computer vision: Develop models on satellite and street-level imagery for text detection, OCR, face recognition, generic object detection and image classification
  • Natural language processing: Develop models of multiple Southeast Asian languages for intent detection, reply suggestions, search query understanding, geographic information extraction, and incident response.
  • Speech processing: Develop models to identify voice commands, detect user-sentiment, and for voice-authentication.
Get to know the role
  • Work with business and product stakeholders to ensure the right technologies are used to solve the right problems.
  • Design and implement algorithms to derive deep insights and identify trends, patterns and relationships from high-volume high-dimensional data.
  • Conceptualise and develop machine learning models to understand, classify and predict user behaviors in different scenarios in Grab’s ecosystem.
  • Develop machine learning models or algorithms for specific use cases similar to the above examples. Deploy, test and maintain them.
  • Design and conduct both offline and online experiments to validate hypotheses
  • Work with engineering teams to productize the outcome. Platformize the technologies to be reusable across Grab wherever possible.
The must have
  • Degree in Computer Science, Electrical/Computer Engineering, Industrial & Systems Engineering, Mathematics/Statistics, or related technical disciplines. Masters and PhD preferred.
  • Expert working knowledge and a couple of years experience in any of the examples above
  • Strong knowledge in mathematics, signal processing, data structure and algorithms.
  • Proficient in one or more of the following programming languages: Python, R, Scala, Golang Java, C++
  • Strong working knowledge of machine learning principles including classification, clustering, anomaly detection, semi-supervised learning, and reinforcement learning.
  • Experience in ETL, feature selection, hyper-parameter optimization, model validation and visualization.
  • Experience in data analysis / numerical computing / classical ML tools like Pandas, NumPy/SciPy, Scikit-Learn, or XGBoost.
  • Experience in deep learning frameworks like Tensorflow or PyTorch.
  • Familiarity with relational databases and SQL
  • Self-motivated, independent learner, and enjoy sharing knowledge with team members.
  • Detail-oriented and efficient time manager in a dynamic fast-paced working environment.
Really nice to have
  • Experience in production software engineering routines such as test-driven development, code versioning with Git, conducting code reviews, and CI/CD.
  • Experience in data analysis and machine learning with cloud platforms (e.g. AWS, Azure, GCP) or modern data processing stacks (e.g. Hive, Presto/Trino, Spark, Kafka, Airflow, HBase, Flink etc.)
  • Proven track record/ accolades in data/ AI-related competitions (e.g. KDD Cup) or programming competitions (e.g. ICPC).
  • Deep understanding of various machine learning and deep learning models, with familiarity dealing with trade-offs.
  • Hands-on experience in developing algorithms and models at a very large scale in an industry environment.
  • Excited about working in a fast-paced and agile environment.
We are committed to building diverse teams and creating an inclusive workplace that enables all Grabbers to perform at their best, regardless of nationality, ethnicity, religion, age, gender identity or sexual orientation and other attributes that make each Grabber unique.
Join us today to drive Southeast Asia forward, together.

Please let the company know that you found this position on this Job Board as a way to support us, so we can keep posting cool jobs.