Senior Data Scientist

About Amplify Health
Who We Are
Amplify Health is Asia’s leading health technology and analytics organisation, providing our customers with integrated solutions to make healthcare more accessible, affordable and effective across the region.

We offer a unique B2B business model and integrated stack of SaaS-based products, PaaS-based Health Tech launchpad and DaaS-based on-demand data offerings to deliver impact to our customers across the healthcare value-chain.

Our joint-venture partners, AIA and Discovery, have provided us with the foundations and a platform that truly differentiates us from our competitors and allows us to build and deploy products at a scale and quality that few can match.

We aim to be the trusted custodian of Asia's largest repository of health data, unifying financial, clinical, operational and behavioural data to empower our customers with insights that highlight opportunities to deliver better value and care outcomes.

The Position
Summary
The  Senior Data Scientist  plays a pivotal role in designing, developing, and deploying advanced analytics and machine learning solutions that deliver actionable insights across healthcare, insurance, and wellness domains. This individual collaborates with cross-functional teams—including data engineers, actuaries, clinicians, and product managers—to transform complex datasets into predictive models and decision-support tools that improve health outcomes and operational efficiency.

The role requires a blend of hands-on technical expertise, curiosity, problem solving and business acumen. The Senior Data Scientist is responsible for end-to-end delivery for AIML work streams from scoping to deployment/monitoring; leads feature engineering strategy; mentors juniors and performs code reviews on top of being hands on.

The ideal candidate thrives in a fast-paced, agile environment and is passionate about leveraging data to solve real-world healthcare challenges.

Responsibilities
1) AIML System Design, Business Problem Framing & Product Thinking
Partner with stakeholders to clarify business questions into ML problem statements (classification, ranking, uplift, forecasting, optimization, GenAI RAG/agentic workflows, etc.).
Define what data is needed (first-/third-party, events, text, image, claims/transactions, IoT), data quality thresholds, and labelling strategy.
Define north-star metrics (online and offline) and decision boundaries; craft counterfactuals and baselines (e.g., business-as-usual) to quantify impact. Connect model metrics to business outcomes.
Write and maintain an ML System Design Spec: problem hypothesis, decision loop, users, constraints, acceptable risk, SLAs/SLOs, and post-deployment guardrails.

2) AI and ML Model Development, Research & Deployment
Data Exploration & Feature Engineering:
Conduct advanced exploratory data analysis on large datasets using Python, pyspark, SQL, and visualization libraries.
Engineer high-quality features leveraging domain knowledge, statistical transformations, and automated feature selection techniques.

Model Development:
Design, implement, and validate machine learning and statistical models to address complex healthcare and insurance challenges.
Explore cutting-edge algorithms (e.g., regression, clarification etc.) and assess their applicability to real-world use cases.
Ensure reproducibility and scalability of models through modular design and robust documentation.

Model Deployment & MLOps
Collaborate with Dev Ops engineers to product ionize models using containerization (Docker), orchestration (Kubernetes), and CI/CD pipelines.
Collaborate with DE team to implement and optimize the feature store
Implement automated monitoring systems for model drift, performance degradation, and data quality issues.
Define retraining strategies and governance protocols to ensure compliance and long-term reliability.

AI/ ML Accelerators Development:
Build and maintain reusable ML accelerators (Cookiecutter, Feature Engineering Toolkit, AutoML , Unified Evaluation Harness, Observability Blueprints, Responsible AI Pack etc) that standardize feature engineering, model training, and evaluation across tasks.

3) Collaboration & Stakeholder…