AI Engineer (Self-Evolving Agent)

42dot
South Korea
Workplace: HybridFull timeFunction: Data Science & Machine LearningExperience: 4+ yearsEducation: mastersSkills: ["Ownership","Collaboration","Critical discussion"]

Build LLM-based vehicle voice AI agent capabilities for real-world production use. You’ll design an agent execution experience with reusable self-improvement loops, connect interaction/execution traces to learning data and evaluation, and develop agentic planning, tool-use, context management, orchestration, and runtime. Experiment with recent research to improve production capability while addressing safety risks and failure modes.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
42dot
42dot
1 day ago

AI Engineer (Self-Evolving Agent)

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 3 hours agoStatus: Live

Job Summary

Build LLM-based vehicle voice AI agent capabilities for real-world production use. You’ll design an agent execution experience with reusable self-improvement loops, connect interaction/execution traces to learning data and evaluation, and develop agentic planning, tool-use, context management, orchestration, and runtime. Experiment with recent research to improve production capability while addressing safety risks and failure modes.
Location: South Korea
Workplace: Hybrid
Employment Type: Full time
Job Function: Data Science & Machine Learning
Seniority: Mid level

Key Responsibilities

  • •Build, evaluate, and improve a self-improvement loop that generates reusable skill/knowledge/strategy/workflows from execution experience and feedback.
  • •Create a data flywheel by linking real-service interactions and execution traces to learning/evaluation data, then validating improved capabilities on real vehicles.
  • •Design agent planning, tool-use, context management, and orchestration; develop agentic AI architecture and an execution runtime for stable execution of complex tasks.
  • •Experiment with recent research and turn findings into production capabilities, addressing safety risks and failure modes discovered along the way.

Key Requirements

  • •M.S. or higher in Computer Science, AI, or related fields, plus 4+ years of hands-on experience in AI/ML or software engineering.
  • •Understand core principles of LLM and agentic AI, and have applied them in real services.
  • •Ability to rapidly interpret new research and validate ideas through hypothesis → experiment → evaluation.
  • •Strong software engineering skills to design, implement, and operate production-level AI/ML systems (prefer Python or Kotlin).
  • •Ownership to define problems without fixed answers and deliver end results to real users.
Experience:4+ years
Education:Master's
Skills:OwnershipCollaborationCritical discussion
Tech Stack:LLMAgentic AIAgent orchestrationTool/function callingMemorySelf-improvement loopData flywheelExecution tracePythonKotlinMulti-AgentMCPA2APrompt InjectionRegression TestingLLM-as-a-JudgeContinuous Learning PipelineTool-use SafetyMemory/Skill PoisoningLatency

Company Brief

42dot
Develops autonomous driving and mobility software platforms, including AI-based perception, mapping, routing, and connected-vehicle technologies. It works on next-generation transportation systems and self-driving vehicle capabilities for automotive applications.
Industry: Autonomous Vehicles
Company Size: Large (251 to 1,000 employees)
Growth: Scaleup
Headquarters: Seoul, South Korea
Founded: 2019
WebsiteLinkedIn