4

42dot

Unified platform for multi-modal urban mobility

AI Engineer - Self-Evolving Agent

Natural Language Processing & LLMsConfirmed live in the last 24 hours
Full-timePangyo-ro, Bundang-gu, Seongnam-si, Gyeonggi-do, South KoreaNo salary listedHybrid

About the Job

Requirements

  • A master's degree or higher in computer science, artificial intelligence, or a related field, and at least four years of professional experience in AI/ML or software engineering.
  • Understand core principles of large language models and agentic AI and have experience applying them to live services.
  • Be able to quickly understand current research and validate its applicability through hypothesis formation, experimentation, and evaluation.
  • Have software development capability to design, implement, and operate production-grade AI/ML systems; Python or Kotlin is preferred.
  • Be able to independently define problems without predetermined answers and deliver results to real users.
  • Be able to discuss matters rigorously based on evidence, align on decisions, and execute collaboratively.

Responsibilities

  • Build a self-improvement loop that creates, evaluates, and improves reusable skills, knowledge, strategies, and workflows from agents’ execution experiences and feedback.
  • Build a data flywheel that turns real-service interactions and execution traces into training and evaluation data, then validates improved capabilities in actual vehicles.
  • Design planning, tool use, context management, and orchestration for large-language-model-based agents; develop agentic AI architecture and execution runtimes that reliably perform complex tasks.
  • Experiment with and validate current research against Gleo’s problems, implement applicable findings as production capabilities, and address safety risks and failure modes.

Desired Qualifications

  • Have researched or implemented self-improvement systems through which agents learn and improve from experience and feedback.
  • Have built or operated agent evaluation, benchmarking, LLM-as-a-judge, or regression-testing systems.
  • Have built a data flywheel or continuous-learning pipeline using large-scale interactions and execution traces.
  • Have researched or applied multi-agent systems, MCP, or A2A in a production service.
  • Have addressed agentic AI safety and failure modes, including prompt injection, memory or skill poisoning, and tool-use safety.
  • Have measured and optimized latency, cost, reliability, or task performance for large-language-model services.
  • Have published papers at major conferences, contributed to open source, or brought research ideas through to production capabilities.
  • Have designed or developed AI/LLM services with device characteristics such as vehicles or mobile devices in mind.

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