Principal Machine Learning Engineer (Marketplace Simulation)

PLT Engineering; Singapore; On-site; USD 80,000 - 120,000; Full time

Job summary

Join a forward-thinking company where you will be at the forefront of technology, building large-scale simulation platforms to enhance marketplace efficiency. This role offers an exciting opportunity to work with cutting-edge machine learning techniques, creating models that address real-world challenges. You will collaborate closely with a dynamic team, driving innovations that impact thousands of users daily. If you are passionate about problem-solving and thrive in a fast-paced environment, this position is perfect for you. Embrace the chance to make a significant impact in a vibrant and evolving industry.

Qualifications

• Experience in building production-ready machine learning systems.
• Strong understanding of software engineering best practices.

Responsibilities

• Build and architect a robust platform for marketplace behavior modeling.
• Collaborate with data scientists to design workflows for policy optimizations.

Skills

Machine Learning

Reinforcement Learning

Simulation Modeling

Data Analysis

Software Development Lifecycle

Education

Bachelor's Degree in Computer Science or related field

Master's Degree in Data Science or related field

Tools

Python

TensorFlow

Jupyter Notebooks

Job description

Get to Know the Team

The Fulfilment Tech family forms a key pillar at Grab, dedicated to delivering services for our consumers and partners across Southeast Asia. You will be part of a team working with cutting-edge technology, developing high-throughput, real-time distributed systems that leverage machine learning to process hundreds of millions of requests daily. Our mission is to enhance driver opportunities and efficiency, ensuring consumer orders are fulfilled seamlessly while creating optimal marketplaces with sustainable and favoured pricing models.

Get to Know the Role

In this hands-on role, you will build large-scale simulation platforms, creating a digital twin representation of Grab's vibrant marketplace encompassing thousands of consumers, drivers, and merchants. You will design and implement advanced models using reinforcement learning and optimization techniques to solve critical business challenges and deploy these solutions at scale.

You should understand software development lifecycle and engineering best practices, coupled with substantial experience in production-ready machine learning systems. You should excel in constructing accurate simulations of complex systems and have expertise in areas like regression, classification, and real-time streaming data analysis.

You are an agile thinker with a passion for innovation and enjoys problem-solving in a rich technical landscape. You will report into the Senior Engineering Manager and work onsite in Grab One North Singapore office. We look forward to having you join our dynamic team!

The Critical Tasks You Will Perform

You will:

• Build and architect a robust platform that models real-world marketplace behaviour across Grab's diverse services.
• Set and drive the integration of the Simulation Platform into product development cycles within Fulfilment Tech.
• Establish design guidelines for components in the Fulfilment System to integrate with the simulation platform.
• Create tools for comprehensive "What-If" scenario analysis to support data-driven decisions regarding product development.
• Collaborate with data scientists and engineers to design workflows that drive platform policy designs and optimizations.
• Develop SDKs to enhance user experience on the platform.
• Partner with data scientists to build feedback loops, allowing policy’s analysis and implementation using simulations.
• Design and scale the simulation platform to conduct numerous simulations daily, while identifying and resolving performance bottlenecks.
• Handle software performance analysis, capacity, demand planning, costing, tuning, and optimization.
• Participate in reviews to ensure adherence to high development standards.