Process Automation Engineer (AI / ML Ops / Data Science Vertical) – Business Intelligence

Shopee; Manila; On-site; PHP 800,000 - 1,200,000; Full time

Job summary

A leading e-commerce platform in the Philippines is seeking an experienced Data Scientist to lead the feature strategy for machine learning projects. The ideal candidate will have a strong statistical background, with at least 2-5 years' experience in data science. Responsibilities include collaborating with business teams to structure operational data for models, evaluating data quality issues, and contributing to experiment design. This position requires a strong communicator who thrives in high-stakes environments.

Qualifications

• 2–5 years of experience in data science, machine learning, or quantitative analytics.
• Strong background in statistics, feature engineering, anomaly detection, and time series.
• Able to work in ambiguous, high-stakes environments.

Responsibilities

• Lead feature strategy for ML and LLM projects.
• Work closely with business teams to translate messy operational processes into structured model inputs.
• Design robust logic to handle entity overlaps.

Skills

Data science

Machine learning

Quantitative analytics

Feature engineering

Statistics

Anomaly detection

Python

SQL

Jupyter

Tools

Spark

Hive

PyTorch

XGBoost

Job description

About The Team

Shopee PH is scaling intelligent systems across Operations, Commercial Team, SPX, Scommerce, etc. As we expand ML deployment in critical domains, we need an experienced Data Scientist who understands both statistical modeling and real -world operational nuance. This role is ideal for someone who thrives in ambiguity, understands the difference between data and domain truth, and is passionate about driving measurable impact through better feature engineering, normalization logic, and experiment design.

Job Description

• Lead feature strategy for ML and LLM projects
• Work closely with business teams (Ops, SPX, Risk, SCommerce) to translate messy operational processes into structured model inputs
• Own EDA, outlier detection, feature construction, and normalizations
• Design robust logic to handle entity overlaps
• Evaluate data leakage, overfitting risks, and data quality issues before ML engineers build pipelines
• Partner with ML engineers to hand off model-ready datasets with clear logic
• Contribute to experimentation plans and model evaluation metrics
• Support knowledge documentation and AI governance compliance

Requirements

• 2–5 years experience in data science, machine learning, or quantitative analytics
• Strong background in statistics, feature engineering, anomaly detection, and time series
• Proficient in Python, SQL, Jupyter (bonus: Spark, Hive, PyTorch, or XGBoost)
• Able to work in ambiguous, high-stakes environments (logistics, fraud, finance, risk, etc.)
• Strong communicator — can explain why a feature matters to business users and engineers
• Familiarity with ML lifecycle, but comfortable focusing on upstream data/feature quality