Research Engineer LLM / English (RT)

Design the Heart of the Enterprise Brain. Build the Control Infrastructure and Guardrails for Autonomous AI Agents!【Residents of Japan】

 

 

■ Job Title

Agent Harness Engineer

 

 

■ Company Overview

We are an elite, fast-growing AI startup building next-generation core enterprise platforms. Our mission is to construct "the brain of the enterprise"—a unified system where AI agents seamlessly integrate with SaaS tools to autonomously execute hundreds of business workflows. We operate an engineering-first culture that brings together top talent to solve complex frontier challenges, balancing cutting-edge research with scalable, real-world product deployment entirely in-house.

 

■ Your Role and Responsibilities 

• Design and implement the agent execution engine (Graph Runtime / State Machine) with a deep technical grasp of LLM and AI agent operating principles.
• Own AI-specific system design, architecting orchestrations, model routing, context processing, and memory infrastructure (working memory and long-term memory).
• Develop and maintain the Agent SDK to be utilized internally by over 120 product and application engineers.
• Architect and refine the guardrail and policy execution engine to guarantee that autonomous workflows operate safely, quickly, and reliably.
• Partner closely with AI Research Engineers to integrate state-of-the-art research findings into production-level agent infrastructure.

 

■ Experience and Qualifications

• Bachelor's degree or equivalent practical experience in Computer Science, Software Engineering, Artificial Intelligence, Machine Learning, Mathematics, Physics, or related fields.
• 5+ years of practical professional experience as a Backend Engineer.
• Extensive production product development experience using Python.
• Proven experience designing and implementing live production systems that leverage LLMs or AI agents.
• Solid experience with the actual design and coding of distributed systems (not limited to operations or infrastructure management).
• Professional proficiency designing and building RESTful APIs or gRPC services.
• Language Skills: Fluent Japanese (able to discuss complex product development without friction) OR Business-level English.

 

■ Tech Stack

• Languages & Frameworks: Python, Go, TypeScript, React, Next.js, NX
• Infrastructure & Cloud: GCP (containers / Kubernetes), Docker, Terraform
• Messaging & Data Flow: Kafka, Pub/Sub
• Monitoring & Observability: Prometheus, Grafana, OpenTelemetry
• AI Development Support: Claude Code MAX Plan, Cursor, ChatGPT, Devin
• Hardware & Tools: Mac (Apple Silicon), dual monitor setup, Slack, Confluence, Linear, Notion, GitHub

 

■ Good Reasons to Join

• Elite AI Developer Support: Access the absolute best tools available, with full company coverage for ChatGPT, Cursor, Devin, and the Claude Code MAX plan.
• Comprehensive Learning Support: Generous assistance for technical books (up to ¥30,000/half-year), paid development tools (up to ¥30,000/year), and specialized language learning/qualification acquisition.
• Flexible Hybrid Work Style: Work 3 days in the office and 2 days remotely with flexible working hours (negotiable core time) and future options for increased flexibility.
• Excellent Living & Welfare Benefits: Includes housing support for designated areas (up to ¥30,000/month) and a monthly "Refresh Allowance" (up to ¥5,000) for gyms, movies, theme parks, or chiropractic care.
• Strong Financial Incentives: High-range base salary, stock options, and performance reviews with bonuses conducted twice a year.

 

■ Work Location

Tokyo (Hybrid Work Style)

 

■ Salary 

¥12,000,000 〜 ¥20,000,000 (Based on experience; bonuses and stock options available)