Senior AI Agent Engineer (Gleo Interactor)

The role

The Gleo Interactor team develops LLM-based interaction systems that connect vehicles and users. You will design and develop AI Agent structures, orchestration, and tool calling to perform vehicle functions based on user requests.

What you will do

• Design and develop the structure and execution methods of LLM-based AI Agents
• Develop Agent Orchestration and Tool Calling based execution structures to perform complex user requests step-by-step
• Control Agent execution feasibility and behavior based on vehicle situations and constraints to prevent incorrect vehicle control and malfunctions
• Develop Conversation Design to design dialogue flows matching user intent and situations and connect Agent behavior and responses
• Build LLM Agent evaluation metrics, datasets, and evaluation environments and improve Agent quality based on evaluation results

Required qualifications

• 8 or more years of relevant experience or equivalent expertise
• High level of design and problem-solving capabilities to structure complex requirements and implement stable AI systems
• Experience understanding and applying key LLM-based system technologies such as Prompt, Context, and Tool Calling to actual services
• Experience designing, building, and analyzing results of metrics, datasets, and evaluation environments to quantitatively and qualitatively evaluate LLM Agent quality
• Ability to quickly learn new AI technologies and apply them to actual products
• Ability to lead technical direction and execute while collaborating with various job functions

Nice to have

• Android / Kotlin based app or vehicle/mobile platform development experience
• Voice / Conversational AI or LLM-based Agent system development experience
• LLM Fine-tuning / Post-training or On-Device AI / LLM development experience
• Embedding-based Semantic Search and Entity Retrieval technology development experience
• Experience in finely controlling Agent behavior and responses and analyzing and improving quality based on user log data

Before you apply

• Interview process includes document screening, coding test, 1st interview (video, approx. 1 hour), and 2nd interview (in-person or video, approx. 3 hours)
• Do not include prohibited information such as resident registration number, family relations, marital status, salary, photo, physical conditions, or hometown in the application
• Employment may be canceled if false information is found in the application
• Reference checks may be conducted after the interview process with the applicant's consent
• A 3-month probation period may apply

About the company

42dot's Gleo Interactor team develops AI Agent technology that naturally connects vehicles and users.