4

42dot

Unified platform for multi-modal urban mobility

AI Agent Engineer - Autonomous Driving

AI Application EngineeringConfirmed live in the last 24 hours
Full-timePangyo-ro, Bundang-gu, Seongnam-si, Gyeonggi-do, South KoreaNo salary listed

About the Job

Requirements

  • Have at least 3 years of experience in Software Engineering, Machine Learning, or AI applications, or equivalent research and development capability.
  • Have experience designing and implementing AI applications or data pipelines using Python.
  • Have experience developing LLM/VLM-based systems that use tool calling or multi-step workflows and evaluating their execution results.
  • Be able to design evaluation metrics and datasets to validate agent decisions and label quality, and analyze failure cases.
  • Have English communication skills sufficient to discuss technical issues and collaborate with overseas offices.

Responsibilities

  • Design the agent reasoning loop and execution structure so that a vision-language model can select and call tools to access driving videos, simulation logs, and evaluation metrics.
  • Develop agent workflows that perform multi-step driving evaluations and failure triage through context management, tool routing, and error recovery.
  • Generate structured pseudo-labels for driving decisions and estimated causal factors based on evidence collected by agents, and improve their quality.
  • Validate agent judgments and label quality using human annotation and counterfactual scenarios, and integrate the workflow into a closed-loop evaluation pipeline.
  • Identify tasks in driving-result evaluation, failure triage, and data generation where agents can contribute; lead their design, experimentation, validation, and integration into evaluation pipelines.

Desired Qualifications

  • Have experience with scene understanding and failure analysis using autonomous-driving data or closed-loop simulation.
  • Have experience with VLM fine-tuning, auto-labeling, or causal reasoning.
  • Have experience developing agent workflows using long-term memory or retrieval, custom tool development, or multi-agent orchestration.
  • Have experience analyzing and improving the reliability and bias of LLM/VLM-based evaluators.

About the Company

42dot

Unified platform for multi-modal urban mobility

42dot.ai provides a platform called UMOS (Urban Mobility Operating System) that connects and manages multiple transportation modes—such as cars and drones—within a single system for cities, agencies, and private clients. UMOS enables efficient transportation management, demand-response services, and smart logistics by integrating data and operations across modes, powering operations through a subscription-based platform-as-a-service model. Unlike single-mode solutions, 42dot.ai offers multi-modal, city-focused orchestration that bridges public, private, and logistics needs. The company aims to transform urban mobility by helping cities run more efficiently, cut costs, and improve the experience for commuters and logistics providers.

Company size
501-1,000
Company stage
Growth Equity (Venture Capital)
Total funding
$731.9M
Headquarters
Seoul, South Korea
Founded
2019

Recently Posted Jobs

Explore more opportunities at 42dot

See more jobs