T

Toss

Fintech super-app for payments and banking

Machine Learning Engineer

Applied Machine LearningConfirmed live in the last 24 hours
Full-timeSeoul, South KoreaNo salary listedIn-person

About the Job

Requirements

  • Experience improving at least one of recommendation systems, search/ranking, or personalization models in a live service.
  • Experience writing model-training, evaluation, and experimentation code with Python and PyTorch is desirable.
  • Ability to validate the context and biases behind data rather than relying on logs and metrics at face value.
  • Ability to define problems by connecting model structure, training data, evaluation methods, and product metrics.
  • Ability to consider serving stability, operational metrics, and deployment risk alongside model performance.
  • Ability to explain complex problems clearly to colleagues and collaborate closely across functions.

Responsibilities

  • Improve the quality of community feed recommendations.
  • Improve personalized recommendation models to connect users' interests with the context of content.
  • Consider community trust and long-term user experience, not only the likelihood of a user reaction.
  • Assess how recommendation results affect the actual product experience and improve both models and service logic.
  • Define and validate training data using user behavior logs and content data.
  • Address recommendation-system quality issues such as exposure bias, selection bias, and data freshness.
  • Improve features that represent user, content, and community context for model decision-making.
  • Build offline evaluation methods that verify whether models that look promising offline also improve the actual user experience.
  • Improve metrics and sampling methods for interpreting and debugging recommendation results.
  • Connect experiment results to product metrics and define subsequent improvement directions.
  • Improve response speed, monitoring, and deployment safety so models can be served reliably.
  • Analyze causes of operational quality degradation and data changes, and make structural improvements.
  • Build recommendation systems that support rapid experimentation and stable operations in collaboration with product, server, and data engineers.
  • Design the direction of community recommendations and directly design and lead recommendation algorithms.

Desired Qualifications

  • Experience improving or operating large-scale recommendation or ranking systems end to end.
  • Experience using representation learning or contrastive learning to improve real service metrics.
  • Understanding of training-data pipelines based on large-scale event logs or feature stores.
  • Experience with online machine-learning operations, including model deployment, experiment management, or monitoring.
  • Experience with text, community/social, or financial-domain data.

About the Company

Toss

Fintech super-app for payments and banking

Toss is a South Korean financial services platform that started as a peer-to-peer money transfer service and has grown into a digital 'super app' for personal finance. Its products are accessed through one mobile interface that unifies bank accounts, credit cards, loans, investments, and other financial services, including its own Toss Bank and Toss Securities. It differentiates itself by offering a broad, integrated ecosystem—combining digital banking, asset management, and brokerage services under one roof and running its own banking and securities units. Its goal is to become the leading consumer finance platform in South Korea while expanding its user base globally.

Company size
1,001-5,000
Company stage
Series G
Total funding
$1.5B
Headquarters
Seoul, South Korea
Founded
2011

Recently Posted Jobs

Explore more opportunities at Toss

See more jobs