Agentic ML Engineer for Fraud Analytics

FPT Asia Pacific; Singapore; Sur place; SGD 90 000 - 150 000; Plein temps

Résumé du poste

FPT Asia Pacific is seeking an ML/AI Engineer embedded in the data analytics and AI division’s fraud analytics team. You will design and build two agentic AI systems that surface emerging fraud risks and translate validated risks into actionable detection logic, with human validation and guardrails throughout.

You will develop end-to-end architectures, integrate with Redshift, Glue and PySpark, and deliver MVPs while building in-house capability to maintain the systems.

Qualifications

• Degree in Computer Science, Artificial Intelligence, Data Science, Software Engineering, Information Systems or related field.
• 3–5 years of hands-on experience building and deploying ML/AI applications, including at least one LLM-enabled system beyond prototype.

Responsabilités

• Design end-to-end agentic AI architecture for fraud analytics solutions.
• Develop AI agents to identify emerging fraud risks and translate validated risks into detection logic.
• Integrate AI workflows with fraud analytics platforms (Redshift, Glue, PySpark).
• Build modular, tested, deployable services with clear interfaces and version control.
• Create automated CI/CD workflows with quality and gate checks.

Connaissances

Python

API development

LLM-enabled systems

Multi-agent frameworks

Data integration

CI/CD

Observability

Governance

Formation

Degree in Computer Science / AI or related

Outils

LangGraph

CrewAI

AWS Bedrock

Redshift

Glue

PySpark

Databricks

Docker

MLflow

GitHub Actions

Jenkins

Description du poste

FPT Asia Pacific is seeking an ML/AI Engineer embedded in the data analytics and AI division’s fraud analytics team. You will design and build two agentic AI systems that surface emerging fraud risks and translate validated risks into actionable detection logic, with human validation and guardrails throughout.

You will develop end-to-end architectures, integrate with Redshift, Glue and PySpark, and deliver MVPs while building in-house capability to maintain the systems.