Tóm tắt công việc
About the role
Ahamove is an on-demand logistics platform handling large daily volumes of orders, drivers and delivery points nationwide. Our Data function is split into two groups: Data Platform owns the infrastructure - warehouse, lake, pipelines, analytics engineering - while Data Science & Analytics, the group you will lead, applies that data through models and AI to improve how the platform performs.
You will build the team on an existing foundation, set how it works, and own the data group's project portfolio end to end.
What you will do
Set the direction for our modeling work - currently dynamic pricing and dispatching, with demand forecasting, matching and operational optimisation as likely next steps.
Identify where machine learning and AI can measurably improve platform performance: pricing efficiency, dispatch quality, driver and customer experience, operational cost.
Own delivery of the data group's projects: scope, prioritise, and drive them through to production alongside product and engineering.
Make sure models reach production, are measured against real business impact, and stay operationally healthy - research that never ships does not count.
Build an experimentation culture: design and evaluate A/B tests for pricing, product and algorithm changes.
Keep the analytics the business relies on accurate and trusted, and use those insights to surface the next opportunity worth modeling.
Lead, coach and grow the team; own hiring as it expands.
Partner with Data Platform on data and feature requirements, and with Backend and
Product Owners to ship model outputs into the product.
Physical Wellbeing Benefit: General Insurance, Medical check-up, Accident Insurance, Healthcare Insurance.
Emotional Wellbeing Benefit: Company Trip, Year End Party, Aha Hour Activities, Special Day Gifts, Aha Club (Badminton, Soccer).
Financial Wellbeing Benefit: Grab/Be For Work (Tech/Lead Level), Workplace Relocation, 13th Month Salary, PP Appreciate, Annual Leave Remain.
6+ years in data (data science, analytics, or a mix), including 2+ years managing a team.
A track record of machine learning work that reached production and moved a business metric.
Background in a data-heavy digital product; marketplace, logistics, fintech, e-commerce or ride-hailing preferred.
Python for modeling and analysis (pandas, scikit-learn or equivalent), and strong SQL on a modern warehouse.
Solid statistical foundations: experiment design, hypothesis testing, careful interpretation of results.
Practical understanding of the full model lifecycle, from research through deployment, monitoring and retraining.
Awareness of the current AI and ML landscape, and judgement about where it genuinely applies to a logistics business.
Enough familiarity with warehouse architecture and analytical data modeling to work effectively with data and analytics engineers.
Communicates complex findings simply and persuasively to non-technical audiences.
Prioritises problems by business value, not technical interest.
Comfortable operating with ambiguity in a fast-moving environment.
Nice to have
Pricing, matching, dispatching or operational optimisation problems.
Geospatial data, mapping or routing.
Experimentation platforms, feature stores, or real-time inference.
Basic Kubernetes knowledge and familiarity with ML workflow tooling (MLflow, Airflow, Kubeflow or similar).