Description
Grab is Southeast Asia's leading superapp, providing various services such as food delivery, financial management, and transportation.
You will join our Search and Recommendations team, a group of machine learning engineers and data scientists who build algorithms that help millions of users discover food, groceries, and services across Southeast Asia.
You will report into the Senior Data Science Manager and work onsite at Grab One North Singapore office. You will design and build machine learning systems that power search ranking and personalized recommendations at scale.
The critical tasks you will perform:
- Design and implement deep learning algorithms for search ranking, session-based recommendations, and multi-objective personalization systems that serve millions of users daily.
- Fine-tune and deploy Large Language Models (LLMs) to improve search query understanding and recommendation relevance.
- Lead offline evaluation design and online A/B testing to validate model performance, ensuring measurable improvements to user engagement before production release.
- Partner with software engineers to scale your models from prototype to production, including model serving optimization and latency requirements.
- Translate data insights into concrete product features by collaborating with product managers and business operations teams, defining requirements based on user behaviour analysis.
- Monitor model performance in production and implement retraining pipelines to maintain prediction quality as data patterns evolve.
To perform these tasks, you will need:
- Master's in Computer Science, Operations Research, Statistics, or equivalent quantitative field, or equivalent practical experience building production ML systems at scale.
- At least 3 years of experience building and deploying deep learning models for search, recommendation systems, or NLP applications in production environments.
- Hands-on experience with Python and Scala to build data pipelines and model serving systems that process high-volume user interaction data.
- Proficiency in at least one deep learning framework (PyTorch, TensorFlow, or JAX) to implement neural network architectures for ranking and sequence modelling.
- Experience with LLM fine-tuning and deployment using frameworks such as Hugging Face Transformers or similar tools to adapt pre-trained models for search and recommendation tasks.
- Demonstrated experience with A/B testing frameworks and statistical evaluation methods to measure model impact on user behaviour metrics.
- Experience deploying models to production using ML serving infrastructure (such as TensorFlow Serving, TorchServe, or cloud-based ML platforms) and optimising for latency constraints.
We care about your well-being at Grab, here are some of the global benefits we offer:
- Term Life Insurance and comprehensive Medical Insurance.
- GrabFlex, a benefits package that suits your needs and aspirations.
- Parental and Birthday leave, and Love-all-Serve-all (LASA) volunteering leave.
- Confidential Grabber Assistance Programme to guide and uplift you and your loved ones through life's challenges.