Get to Know the Team
The Integrity team is dedicated to Trust, Identity, and Safety, safeguarding our users and transactions on Grab. We leverage our datasets to address critical challenges, protecting millions of users and transactions from fraudulent activities, identity compromises, unsafe offline interactions, and harmful platform content. Our core mission involves analyzing ambiguous threat patterns, building anomaly detection, and ideating on new signals to detect risks. To achieve this at scale, we use advanced AI, machine learning, and auto-adaptive systems as powerful tools to enhance our broader risk analysis and decision-making capabilities.
Get to Know the Role
Reporting to the Analytics Manager, you will be an important analytics partner focused on Trust and Safety for a specific Problem Space Team (PST). Your primary focus is to analyze user behavior and product funnels to identify potential risks. You will use our evolving auto-adaptive tools and GenAI capabilities to streamline your daily analytical workflow.
You will base onsite at our Grab Malaysia office.
The Critical Tasks You Will Perform
- Address analytical problems of low to medium complexity, delivering reliable and accurate insights to measure business and product risk performance.
- Analyze user behavior data to identify potential vulnerabilities across different risk domains, including account security, user safety, and content integrity, assisting in the building of anomaly detection systems.
- Ideate on new signals to detect risks, working with stakeholders to develop data-driven rules that mitigate bad actors.
- Use GenAI tools (like Cursor or Gemini) and basic system-thinking to automate routine metric reviews and alerts, freeing up your time for deeper threat investigations.
- Use components of our Auto-Adaptive risk frameworks as tools to help in the operational validation and refinement of safety and risk rules.
- Contribute to foundational data initiatives, such as metric onboarding, data pipeline cleanups, and architectural efficiency, ensuring the data we use for risk detection remains robust and reliable.
