Design and calibrate risk rules and decision frameworks for fraud and credit risk mitigation across e-wallet products, including merchant risk monitoring and BNPL onboarding assessments.
Leverage AI-powered tools (e.g., LLM assistants, AI code copilots, generative AI) as part of the day-to-day analytics and modelling workflow — from exploratory data analysis and feature engineering to report generation and documentation.
Analyze large-scale transaction datasets to uncover fraud patterns, merchant risk indicators, and anomalous user behaviours using SQL-based analytics on cloud data platforms....
Agentic AI Development: Design and develop agentic AI applications leveraging Large Language Models (LLMs), multi-agent frameworks, and orchestration platforms.
AI Agent Engineering: Build, test, and optimize AI agents capable of autonomous reasoning, planning, tool usage, and task execution.
Systems Integration: Integrate AI agents with enterprise systems, APIs, databases, and business workflows to enable real-world use cases....
Lead Data Science Initiatives: Drive AI/ML initiatives supporting Singtel’s product and service offerings by working closely with stakeholders from Marketing, Product, and external partners. Define problem statements and architect end-to-end solutions—including the use of Generative AI and LLMs where applicable—to align with strategic objectives, regulatory requirements, and partner needs.
Model Development & Integration: Design, build, and productionize analytical models that enable intelligent decisioning within customer journeys. Integrate these models into customer-centric decision engines while championing best practices around model governance, scalability, explainability, and continuous performance monitoring.
Customer Behavior & Lifecycle Analysis: Leverage customer behavioral data across Singtel’s Mobile, Broadband, and entertainment services to uncover actionable insights. Maintain and enhance analytical models that inform segmentation, product targeting, and value-based engagement strategies. Enable data exploration, insight discovery, and controlled experimentation (e.g., A/B testing, uplift modeling) to support lifecycle marketing and campaign optimization....
Background in data science, statistics, machine learning, or related quantitative disciplines with demonstrated experience applying analytical techniques to both structured and unstructured datasets
Proficiency in Python and SQL for data analysis, modeling, and data pipeline development, with experience in machine learning model deployment or productionization
Experience with unstructured data processing, particularly text or language data using natural language processing, language models, or text analytics techniques...
Prepare decision-ready data. Combine authorized primary research, market sources and enterprise inputs. Standardize units, time periods and definitions; resolve duplicates, missing values and outliers; retain source lineage and data-quality tests.
Build and compare models. Develop baselines and suitable forecasting, segmentation, scoring or optimization models. Document the business target, assumptions and limits; select complexity only where it improves validated performance or decision usefulness.
Validate and simulate. Use suitable time-based or held-out testing; check sampling bias, leakage and sensitivity. Quantify uncertainty where supportable; distinguish analyst scoring, statistical prediction and causal inference....
Business Advisory & Data Quality Consulting: Partner closely with data creators, stewards, consumers, and IT teams to establish data quality dimensions, rules, and indicators that ensure our data remains usable, timely, robust, and compliant
Framework & Policy Design: Design and maintain policies, methodologies, guidelines, and metrics for data quality, profiling, and cleansing
Rule Definition & Profiling: Collaborate with business stakeholders to identify critical data attributes, profile datasets, analyze requirements, and translate business logic into automated data quality rules...
Own the end-to-end modeling and estimation behind promotion optimization — elasticity, heterogeneous treatment effects, budget-constrained allocation, and increamentality — from problem framing to production.
Advance our causal inference stack: experiment and quasi-experiment design (geo/switchback tests, holdouts, diff-in-diff, synthetic control), debiasing observational data, and variance reduction — raising the bar on experimentation rigor across the team.
Design and productionize heterogeneous treatment effect (uplift) models at scale (tens of millions of users), with honest offline evaluation (uplift/Qini curves, policy-value estimation)....
Build and operate shared AI platforms: a multi-provider LLM gateway, an agent orchestration layer, an evaluation and monitoring layer, and a staff assistant.
Deliver LLM and agent applications for business units, from prototype to live service with measurable business results.
Evaluate AI systems: build test sets; measure groundedness, factual accuracy, task-success rate, safety, latency, reliability and model or data drift; define release gates and rollback criteria; manage model upgrades and retirements....
You will partner with product, design, and engineering teams to obtain insights, design experiments, and guide important product decisions.
You will support strategic plans with data insights, performing deep-dives into user behaviour, segmented views and product efficacy.
You will provide tailored analysis for specific products and strategies, define critical business and product metrics, and make regular recommendations for continuous improvements....
Design and optimise hybrid lexical–semantic retrieval pipelines (e.g., BM25, dense vectors, HNSW/LSH, generative retrieval) to improve precision and recall across GoFood and GoPay surfaces.
Build high-quality embeddings and relevance signals that capture user intent, cuisine and dish semantics, geolocation, delivery constraints, price sensitivity, and promotions.
Develop multi-task deep ranking models that balance conversion, diversity, merchant quality, and long-term user retention, integrating real-time signals such as promotions, surge, and stock availability....
Work as part of a cross-functional team of engineers, product managers and business analysts to build data science solutions that build customer engagement and help grow GoPay’s customer base and transactions.
Rapidly prototype data science solutions and be involved in product and feature discussions
Analyze large volume data and generate insights which will be actionable....
Build and operate shared AI platforms: a multi-provider LLM gateway, an agent orchestration layer, an evaluation and monitoring layer, and a staff assistant.
Deliver LLM and agent applications for business units, from prototype to live service with measurable business results.
Evaluate AI systems: build test sets; measure groundedness, factual accuracy, task-success rate, safety, latency, reliability and model or data drift; define release gates and rollback criteria; manage model upgrades and retirements....
Participate in the design and development of algorithm strategies for user growth, including but not limited to user segmentation, intelligent recommendation, and incentive strategy optimization.
Build user lifecycle models (LTV prediction, churn warning, conversion prediction, etc.) based on user behavior data to drive precision operations and decision-making.
Design and implement A/B testing experiments to evaluate the effectiveness of growth strategies and drive continuous iteration and optimization....
Develop, test and maintain data analytics, machine learning and AI-assisted automation solutions using tools such as Python, SQL, Power BI, Power Automate, Alteryx or similar technologies.
Perform data extraction, cleansing, transformation, validation and exploratory analysis to support audit, assurance and internal innovation use cases.
Support the development of AI and machine learning prototypes, including feature engineering, model evaluation, prompt engineering, retrieval-augmented generation concepts and responsible use of large language models where applicable....