T

Toss

Fintech super-app for payments and banking

AI Platform Engineer - Inference Pipeline

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

About the Job

Requirements

  • Experience designing and operating large-scale data-processing pipelines using LLM or ML models for live services, at tens-of-millions scale.
  • Experience handling large-scale traffic using asynchronous request/result separation or large-batch processing.
  • Ability to understand the LLM ecosystem and assess trade-offs among pay-as-you-go pricing, PTU reserved throughput, and Batch API based on cost and throughput.
  • Experience designing rate limits, redundancy, failover, fallback, and retry mechanisms to keep pipelines operating during failures.
  • Ability to diagnose throughput bottlenecks quantitatively and make explicit trade-offs.
  • Experience setting technical decision criteria, explaining complex topics clearly, and leading collaboration across multiple teams.

Responsibilities

  • Combine ML, LLM, and vision models to automate high-volume judgment tasks in large-scale AI pipelines.
  • Connect Toss's AI platform and infrastructure to the needs of different domains, promote repeated domain requirements into shared capabilities, and mature the platform.
  • Evaluate whether to use external model APIs or migrate to in-house models based on cost and performance, and build a transition path to in-house models as data accumulates.
  • Design cost structures combining pay-as-you-go usage and PTU reserved throughput, and continually identify ways to produce the same results at lower cost.
  • Design asynchronous request/result separation or large-batch processing for workloads that cannot be handled synchronously, maintaining throughput under burst loads.
  • Design rate limits, redundancy, failover, fallback, and retry mechanisms to ensure operational reliability.
  • Monitor end-to-end multi-model pipelines, validate metrics at each stage, and align technical decisions across product, ML, and infrastructure teams.

Desired Qualifications

  • Experience designing and operating multimodal pipelines that process images and text together.
  • Understanding how ML, LLM, and vision models work, and ability to debug issues directly and modify model code.
  • Experience automating high-volume human judgment tasks using LLMs.
  • Experience serving in-house models alongside external model APIs and optimizing inference performance.

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