T

Toss

Fintech super-app for payments and banking

ML Engineer

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

About the Job

Requirements

  • Develop machine-learning models and apply them in production services, including classification, information extraction, similarity learning, and clustering.
  • Train and evaluate models using data and problem characteristics; the posting names PyTorch, scikit-learn, LightGBM, and XGBoost as tools.
  • Apply feature engineering and data modeling to complex, incomplete, or imbalanced data.
  • Consider data leakage, class imbalance, and generalization to new products when designing evaluations; assess precision, recall, and automation rates.
  • Analyze errors in product classification and matching to identify whether labels, features, training-data distributions, or models need improvement; design experiments to test hypotheses and determine next steps from evaluation results and error cases.

Responsibilities

  • Build models and data structures to understand products, using text, images, and structured data to classify categories and extract brands, purchase options, and product attributes; organize product information into consistent schemas and design features and embeddings for recommendations and search.
  • Find and link identical products by searching for matching candidates at scale, developing models to determine whether products are the same, structuring product-group and option relationships, and detecting incorrectly merged or separated products.
  • Improve product-data quality and operational efficiency by analyzing errors in classification, attribute extraction, and matching; automate product review and anomaly detection; connect review outcomes to training data; and combine machine learning with rules to expand automated processing.
  • Build data collection and transformation, model training, batch inference, and online inference pipelines; establish evaluation criteria with recommendation, search, and operations teams; and manage quality, processing speed, and cost as new products and data changes arise.
  • Use curated data in product-name composition and search-quality evaluation.

Desired Qualifications

  • Experience with entity resolution, metric learning, embedding-based candidate retrieval, or approximate nearest neighbor search.
  • Experience processing data with SQL and Spark and building training and inference pipelines; model serving, batch processing, model and data versioning, and monitoring experience.
  • Experience applying hard negative mining, active learning, or knowledge distillation to improve quality and efficiency.
  • Experience working with commerce data such as product catalogs, product matching, attribute extraction, or taxonomies.
  • Experience using text and image embeddings together, or generating and validating training data with large language models.
  • Experience collaborating with recommendation or search teams to provide product features and validate their impact in production services.

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