AI Engineer (Navigation Agent)

42dot
South Korea
Workplace: HybridFull timeFunction: Data Science & Machine LearningSkills: ["Collaboration","Rapid learning"]

Build and improve an LLM-based Navigation Agent that understands user intent and movement context to perform navigation actions. You’ll handle LLM fine-tuning and post-training (instruction tuning, supervised fine-tuning, preference optimization), develop ML components for classification/prediction/ranking, design evaluation metrics, and optimize model accuracy, stability, and response latency in production. Collaborate across Navigation, Backend, Data, and Product to ship and continuously iterate.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
42dot
42dot
1 month ago

AI Engineer (Navigation Agent)

✓ Verified Job

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

Source: Company careers pageValidated by: Fursa AI
Last checked: 52 minutes agoStatus: Live

Job Summary

Build and improve an LLM-based Navigation Agent that understands user intent and movement context to perform navigation actions. You’ll handle LLM fine-tuning and post-training (instruction tuning, supervised fine-tuning, preference optimization), develop ML components for classification/prediction/ranking, design evaluation metrics, and optimize model accuracy, stability, and response latency in production. Collaborate across Navigation, Backend, Data, and Product to ship and continuously iterate.
Location: South Korea
Workplace: Hybrid
Employment Type: Full time
Job Function: Data Science & Machine Learning

Key Responsibilities

  • •Perform LLM fine-tuning and post-training for the Navigation Agent, including instruction tuning, supervised fine-tuning, and preference optimization.
  • •Develop agent models that understand user utterances and movement context to execute navigation functions, including intent/info extraction and tool/API planning.
  • •Build agent component models using traditional ML methods such as classification, prediction, and ranking.
  • •Create training and evaluation datasets and improve data quality.
  • •Design evaluation metrics, analyze failure cases, and optimize accuracy, stability, and response speed in production service environments.

Key Requirements

  • •Experience in Machine Learning or Deep Learning research and development.
  • •Hands-on experience performing LLM fine-tuning or post-training.
  • •Experience designing, training, evaluating, and optimizing models using Deep Learning frameworks such as PyTorch.
  • •Experience developing ML models (e.g., classification, prediction, ranking, recommendation) and improving performance.
  • •Ability to design and build training data and solve model problems through quantitative and qualitative evaluation.
Skills:CollaborationRapid learning
Tech Stack:LLMMachine LearningDeep LearningPyTorchInstruction TuningSupervised Fine-TuningPreference OptimizationTool UseFunction CallingGPU distributed training

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