LiftmyCVLiftmyCV
GB

Machine Learning Engineer

GBGHybridKuala Lumpur, MY
AI job summary

Join GBG as a Machine Learning Engineer and leverage your expertise in machine learning to advance fraud detection solutions for banking and fintech clients. You'll collaborate with software engineers and data scientists to develop and deploy ML models, build MLOps pipelines, and optimize real-time transaction processes. Ideal candidates will have strong experience in ML engineering, particularly in financial environments, and a passion for staying current with AI advancements.

Job description

Enabling safe and rewarding digital lives for genuine people, everywhere

We make it our mission to ensure more genuine people have digital access to opportunities, and businesses have access to more genuine people. Our technology draws on diverse and reliable data to create a single point of truth for identity and address verification. With over 30 years of experience behind us our team and technology are focused on enabling safe and rewarding digital lives for everyone. Regardless of age, location or background, genuine people everywhere should be able to digitally prove who they are and where they live.

About the team and role

The team provides decision support solutions to address business objectives in risk prevention and fraud detection. We deliver software solutions and offer client support using our expertise and a client-focused approach. Machine Learning Engineer Working closely with Software Engineering, Product and Data Scientist teams, the Machine Learning Engineer will advance ML capabilities within the GFS fraud detection platforms. You will work on the delivery of the ML roadmap and building robust MLOps pipelines. You will apply your expertise in machine learning to real-world fraud detection challenges faced by banking and fintech customers globally.

What you will do

  • Design, develop, and deploy machine learning models for fraud and AML detection, supporting both batch and real-time transaction scoring scenarios.
  • Build and maintain MLOps pipelines covering model training, validation, deployment, monitoring, and retraining workflows using modern tooling (e.g. MLflow, Tecton, or equivalent feature stores).
  • Collaborate with data engineers to design feature engineering pipelines and maintain the Predator feature dictionary and sync mechanisms.
  • Optimise model performance to meet strict latency and TPS targets required for real-time fraud decisioning.
  • Conduct model validation, A/B testing, permutation importance analysis, and champion/challenger evaluations to ensure model quality.
  • Work with the Architecture Review Committee (ARC) to align ML platform choices with the overall modernization architecture.
  • Stay current with advances in fraud detection ML — including graph-based models, anomaly detection, and generative AI applications — and propose relevant adoptions.
  • Mentor junior team members and contribute to knowledge sharing across squads.

Skills we’re looking for

  • Strong experience in a ML Engineering environment preferably from the banking, financial services and/or Fintech industries.
  • Strong proficiency in Python for machine learning development; experience with scikit-learn, XGBoost, LightGBM, and deep learning frameworks.
  • Hands-on experience with MLOps tooling: experiment tracking, model registries, feature stores (e.g. MLflow, Feast, Tecton), and CI/CD for ML pipelines.
  • Experience deploying ML models in production environments with strict latency and throughput requirements, preferably in fraud detection or financial crime use cases.
  • Familiarity with ONNX model runtime and serving infrastructure for low-latency inference.
  • Understanding of ML explainability methods, particularly SHAP (Shapley values) and permutation importance.
  • Experience with relational databases (SQL Server, PostgreSQL, Oracle) and data pipeline tooling relevant to ML feature engineering.
  • Working knowledge of cloud-native ML platforms (AWS SageMaker, Azure ML, GCP Vertex AI) and containerisation (Docker, Kubernetes).
  • Familiarity with streaming/CDC data architectures (Kafka, RisingWave, or similar) as inputs to real-time ML feature computation.
  • Experience in Agentic AI technologies is a major plus.
  • Experience with fraud detection modelling concepts: anomaly scoring, supervised classification, network/graph features, and false positive reduction.
  • Solid software engineering fundamentals: version control (Git), code review, unit testing, and Agile delivery practices.
  • Familiarity with Agile based squad environment and cadences.
  • Intellectually curious with a drive to stay current with the rapidly evolving AI/ML and MLOps landscape.
  • Detail-oriented with a strong focus on reproducibility, model reliability, and production-grade code quality.

To find out more

As an equal opportunity employer, we are dedicated to creating a diverse and inclusive workplace where everyone feels valued and empowered. Please inform your GBG Talent Attraction Partner if you require any reasonable adjustments to the interview process.

Job details

Published
May 29, 2026
Job source
jworkable
Workplace
Hybrid · Kuala Lumpur, MY
First seen
May 29, 2026
AI match explained

See how well you match this job

Log in or sign up and Eva will compare your profile with this role, explain your strengths and show what to improve.

Sign up to see your matchAlready have an account? Log in

More at GBG

Similar jobs from this company

None listed.

Across the market

Similar jobs from other companies

Third-party content disclaimer

Full job descriptions are sourced directly from third-party applicant tracking systems (ATS), job boards, recruitment platforms, and employer career pages.

LiftmyCV does not claim ownership of this content or guarantee its accuracy or current availability. All original content is the intellectual property of the respective employers or other rights holders.

LiftmyCV hiring intelligence, availability checks, and related-job recommendations are generated from LiftmyCV data and public sources.

If you prefer, you may apply directly via the original listing for transparency.