Lead Machine Learning Engineer

GRABTAXI HOLDINGS PTE. LTD.; Singapore; On-site; SGD 70,000 - 90,000; Full time

Job summary

A leading Southeast Asian tech firm is seeking a Lead Machine Learning Engineer to develop large-scale user behavioral platforms and personalized recommendation systems. This role requires expertise in Deep Learning and Reinforcement Learning, with responsibilities including designing intelligent ML systems and conducting performance analysis. Applicants should have at least 2 years of experience in machine learning services and proficiency in Python and deep learning frameworks. Opportunity to work in Singapore within a dynamic team.

Qualifications

• At least 2 years of proven experience in DL research, domain of LLMs.
• Experience building complex machine learning services.
• Strong knowledge of Python and deep learning frameworks.

Responsibilities

• Develop and architect a user behavioral platform using DL and LLM technologies.
• Design recommendation engines based on user behavioral models.
• Conduct performance bottleneck resolutions and debugging.

Skills

Deep Learning (DL) research

Reinforcement Learning (RL)

Python programming

Machine Learning services

Statistical modeling

Big data frameworks (e.g., Spark)

Qualitative coding

Tools

PyTorch

TensorFlow

Airflow

MLFlow

Job description

Get to know the Team

The Fulfilment Tech family is one of the pillars that enable Grab to out-serve our consumers and partners in different businesses and marketplaces across Southeast Asia. We are developing high-throughput, real-time distributed systems that use sophisticated machine learning techniques to handle hundreds of millions of requests per day. Our mission is to provide the best-in-class products and experiences to our driver partners, thereby increasing the adoption and engagement of our services. Improve driver partner opportunities and efficiency to fulfil consumer orders without fail, rain or shine. And to create efficient marketplaces by determining an optimal price that is both sustainable and loved by our partners and consumers.

Get to know the Role

As a Lead Machine Learning Engineer, you'll report into the Senior Engineering Manager and work onsite at Grab One North Singapore office. This hands‑on role focuses on developing and deploying large-scale user behavioural platforms. The core responsibility involves building advanced behavioural models of our customers, driver, and merchant partners. These models will power personalised recommendation systems, enhancing the experiences of our drivers and merchants.

You'll design and productionise intelligent ML systems to perform large-scale "what if" scenario simulations, predicting aggregate behavioural changes across our users in response to factors like pricing shifts, incentive changes, or fluctuating demand. The resulting insights will be crucial for driving decision‑making and shaping policy across the organisation.

The Critical Tasks You Will Perform

• Develop and architect a unified user behavioural platform using the latest Deep Learning (DL) and Large Language Models (LLMs) technologies to model the real-world marketplace behaviour across Grab's customers.
• Design and build state-of-the-art recommendation engines based on user behavioural models to personalise our driver partners' experience on our platform.
• Design the User Behavioural Platform to allow comprehensive "What-If" scenario analysis, facilitating data-driven product decisions.
• Define and drive the technical roadmap for integrating the user behavioural platform into more product lifecycles within the Fulfilment Tech Family.
• Set the technical design guidelines for Fulfilment System components to adopt and integrate with the user behavioural platform.
• Develop and integrate both statistical models (e.g., Mixed Logit for utility maximization and discrete choice) and advanced generative models (e.g., RL, Transformer-based, or LLM-driven agents) for modeling user/driver action sequences and responses to platform changes.
• Collaborate with product managers and engineers to design simulation workflows that support platform policy designs and optimizations.
• Identify and resolve performance bottlenecks and debug model accuracy issues, and improve the model performance.
• Conduct service capacity and demand planning, software performance analysis, costing, tuning, and optimization.
• Participate in code and design reviews to uphold high development standards.

What Essential Skills You Will Need

• You have at least 2 years of proven experience in DL research, in the domain of LLMs, and at least 2 years of industry experience building complex machine learning services as a core contributor.
• You can develop and integrate sophisticated models, such as those based on Reinforcement Learning (RL), Transformer architectures, or LLMs, to solve real-world business challenges.
• You have experience implementing and improving LLM post-training pipelines: SFT, RL, RLHF.
• You have engineering skills in Python and deep learning frameworks (e.g., PyTorch, Jax, TensorFlow), with experience building high‑quality research prototypes and systems.
• You have experience modelling behavioural models of complex recommender systems.
• You have understanding and experience with statistical models like discrete choice modelling (e.g. Mixed Logit for utility maximisation).
• You have an understanding of software engineering practices and design patterns, experience writing readable, maintainable and testable code.
• You have experience turning business problems into ML/AI-projects.
• You have experience developing and productionising ML Pipelines using modern technologies such as Airflow, MLFlow.
• You have experience with any big data framework, such as Spark.
  

You may also place a direct application via https://smrtr.io/wMsFq