ML Engineer - Supply Chain AI

About the Company

Our client is an AI startup specializing in smart supply chain solutions across Southeast Asia, focusing on demand forecasting and inventory optimization. The company values agility and an engineering-driven culture where developers have significant ownership over their projects.

Role Overview

This ML Engineer position requires bridging the gap between the data science models created and their deployment into production environments. This role involves hands-on work at the convergence of machine learning engineering and infrastructure, building scalable and dependable systems. You'll be instrumental in defining the ML systems architecture from scratch, impacting products utilized by leading retailers in the SEA region.

Key Responsibilities

• Lead the deployment and operationalization of ML models, developing infrastructure that transitions models from development phases to live production systems.
• Create and sustain ML platform tools including experiment tracking, model versioning, registries, and automated deployment pipelines using platforms such as MLflow and Airflow.
• Design and implement monitoring solutions to detect model drift and maintain prediction accuracy over time.
• Develop automated retraining workflows to ensure models stay updated with evolving data distributions.
• Collaborate with data scientists to design self-service tools allowing easier deployment and iteration of models.
• Manage ML workloads on cloud vendors like AWS, GCP, or Azure leveraging Docker containers, Kubernetes orchestration, and CI/CD pipelines.

Qualifications and Skills

• Between 2 to 5 years of direct experience in machine learning engineering or a similar capacity.
• Proven track record of deploying models to production environments, beyond just model creation or training.
• Hands-on familiarity with ML lifecycle management tools such as MLflow, Apache Airflow, Kubeflow, SageMaker, or Vertex AI.
• Experience implementing model monitoring and drift detection mechanisms.
• Proficiency with containerization (Docker), orchestration (Kubernetes), and continuous integration/delivery methodologies.
• Experience working with cloud platforms like AWS, Google Cloud Platform, or Microsoft Azure.
• Strong command of Python programming coupled with solid software engineering principles.

Additional Advantages

• Prior exposure to AI applications in supply chain domains, including demand forecasting and inventory optimization.
• Knowledge of traditional machine learning techniques such as time-series forecasting, gradient boosting methods, and optimization approaches rather than solely generative AI or language models.
• Experience with constraint programming frameworks, notably Google OR-Tools.
• Familiarity with infrastructure-as-code tools like Terraform and Helm.