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.
Get to know our Team:
Grab’s Fulfilment-Dispatch Data Science team works on challenging and fascinating problems surrounding Grab’s allocation capabilities — ensuring our passengers, driver-partners, consumers and merchants enjoy a reliable fulfilment experience.
Allocation is simply this question: “Given a new booking request, which driver-partner is the best match for this booking, accounting for all other pending bookings now, and all potential bookings and driver-partner movements in the future?” Efficiently solving this problem requires working on domains and techniques such as statistical/machine/deep-learning-based prediction, optimization, simulation, graph theory, offline and online learning of contextual parameters, and geospatial data mining. We apply these techniques on our high-volume high-velocity datasets to drive optimal business outcomes.
We foster a culture where we enjoy raising the bar constantly for ourselves and others, and that strongly supports the freedom to explore and innovate. We are looking for candidates who are excited to work on challenging problems, who can apply their breadth and depth of knowledge to design innovative solutions, and who push boundaries in improving the growing suite of allocation-related services for our users.
Get to know the role:
- Design creative scalable allocation methods that adapt to changing market conditions
- Understand business needs, identify areas for investigation, translate them to technical problems to be solved
- Build, deploy and own production-grade models and services as they serve millions of requests every day
- Iterate on existing allocation features to drive continual improvement
The day-to-day activities:
- Research, analyze high-volume high-velocity data, build quick prototypes, and engineer them into production
- Design data pipelines and conduct experiments to measure the impact of your work
- Effectively communicate results and their implications to business/product stakeholders
The must haves:
- PhD or Master’s degree in Computer Science, Electrical/Computer Engineering, Industrial & Systems Engineering, Operations Research, Mathematics/Statistics, Transportation Engineering, or related technical disciplines with 3+ years of DS work at a technology company; or equivalent experience
- Strong Machine Learning fundamentals:
- Understanding of machine learning algorithms and their ecosystem (data, model persistence, tooling, development lifecycle)
- Experience in developing production-grade ML systems including exploratory analysis, feature engineering, developing data pipelines, observability and maintenance etc.
- Strong aptitude in statistics and large-scale data analytics:
- Understanding of probability and statistics (e.g. hypothesis testing, modeling distributions / regressions, Bayesian statistics etc)
- Experienced in running live experiments (A/B tests, randomized controlled trials) and analyzing their results
- Experienced with relational databases, SQL, and distributed computing frameworks (Spark, Kafka stream processing)
- Strong software development skills:
- Proficient in Python. Skill in Golang, Scala or Rust is an advantage.
- Familiar with Git-based source control, code reviews, test-driven development, cloud-based development (AWS/Azure)
- Self-motivated, independent learner, and willing to share knowledge with the team
- Detail-oriented and efficient time manager in a dynamic working environment
- Able to communicate well in English both verbally and in written communication, as well as convey data insights and results with effective visualizations.
Nice to have:
- Experience in working with geospatial/mobility/logistics data
- Experience in designing probabilistic models at scale in production
- Familiar with modern data pipeline and warehousing stacks (e.g. Hive, Pinot, Airflow, Presto/Trino etc)
- Expertise in any of these specialized domains: graph theory/processing, optimization of stochastic problems, agent-based simulation, adaptive control, reinforcement learning
- Experience with designing, deploying and maintaining microservices (e.g. on Docker / Kubernetes) to serve production models is a big plus
Our Commitment
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.
