ML Engineer - Supply Chain AI

Space Executive; Singapore; On-site; SGD 90,000 - 150,000; Full time

Job summary

Space Executive is seeking an ML Engineer in Singapore to bridge data science and production. You will operationalise models, build ML platform tooling, and ensure robust monitoring and retraining pipelines across cloud environments.

In this greenfield role, you will shape ML systems from the ground up, collaborating with data scientists to enable self‑serve model deployment and iteration for a product used by regional retailers.

Qualifications

• 2–5 years of hands-on ML engineering experience.
• Experience deploying ML models into production.
• Hands-on with ML lifecycle tools (MLflow, Airflow, Kubeflow, SageMaker, Vertex AI).
• Model monitoring and drift detection in production environments.
• Comfortable with Docker, Kubernetes, and CI/CD pipelines.
• Cloud experience on AWS, GCP, or Azure.
• Strong Python skills with software engineering fundamentals.
• Experience with supply chain AI (demand forecasting, inventory optimization).
• Familiarity with traditional ML models (time-series forecasting, gradient-boosted trees).
• Experience with constraint programming tools like Google OR-Tools.
• Infrastructure as code experience (Terraform, Helm).

Responsibilities

• Own the deployment and operationalisation of ML models into production.
• Build and maintain ML platform tooling: experiment tracking, model versioning, registry, and automated deployment pipelines.
• Implement model monitoring and drift detection in production environments.
• Build automated retraining pipelines to keep models relevant as data changes.
• Collaborate with data scientists to build self-serve tooling for deployment and iteration.
• Deploy and manage ML workloads on cloud platforms using Docker, Kubernetes, and CI/CD pipelines.

Skills

Python

Production ML deployment

ML platform

Docker

Kubernetes

CI/CD

Cloud (AWS/GCP/Azure)

ML lifecycle tooling

Model monitoring

Git & software basics

Tools

MLflow

Airflow

Kubeflow

SageMaker

Vertex AI

Docker

Kubernetes

CI/CD

Terraform

Helm

Job description

Our client is an AI startup building intelligent supply chain solutions across Southeast Asia — from demand forecasting to inventory optimisation. They're a lean, engineering‑first team that moves fast and gives engineers real ownership over the products they build.

The Role

They're looking for an ML Engineer to bridge the gap between data science and production — taking models built by their data science team and operationalising them into reliable, scalable systems. This is a hands‑on role sitting at the intersection of ML engineering and platform infrastructure.

This is a greenfield opportunity — you'll be shaping how they build and operate ML systems from the ground up, with direct impact on a product used by major retailers across SEA.

What You'll Do

• Own the deployment and operationalisation of ML models into production — building the infrastructure that takes models from development to live business systems
• Build and maintain ML platform tooling — experiment tracking, model versioning, model registry, and automated deployment pipelines using tools like MLflow and Airflow
• Implement model monitoring and drift detection to ensure production models stay accurate over time
• Build automated retraining pipelines so models stay relevant as data patterns change
• Work closely with data scientists to build self‑serve tooling that enables them to deploy and iterate on models independently
• Deploy and manage ML workloads on cloud platforms (AWS, GCP, or Azure) using Docker, Kubernetes, and CI/CD pipelines

What We're Looking For

• 2–5 years of hands‑on experience in ML engineering or a closely related role
• Practical experience deploying ML models into production — not just building or training them
• Hands‑on experience with ML lifecycle tools — MLflow, Airflow, Kubeflow, SageMaker, Vertex AI, or similar
• Understanding of model monitoring and drift detection in production environments
• Comfortable with Docker, Kubernetes, and CI/CD pipelines
• Cloud experience on AWS, GCP, or Azure
• Strong Python skills with solid software engineering fundamentals
• Experience with supply chain AI — demand forecasting, inventory optimisation, or similar
• Familiarity with traditional ML models (time‑series forecasting, gradient‑boosted trees, optimisation) rather than purely GenAI/LLM work
• Experience with constraint programming tools like Google OR‑Tools
• Infrastructure as code experience (Terraform, Helm)