Agent Harness Engineer
Company
AI Technology Company
Employment Type
Full-time
Location
Nishi-Shinjuku, Tokyo
Work Style
Hybrid — 3 days in office / 2 days remote
Salary
12,000,000 – 20,000,000 JPY annually
About the Company
A rapidly growing AI-native technology company developing enterprise AI products and infrastructure platforms. The organization is focused on building next-generation AI systems that integrate enterprise SaaS environments and enable AI agents to safely execute business operations at scale.
Role Overview
The company is seeking an Agent Harness Engineer to design and build the core execution infrastructure behind production AI agents.
This position focuses on the infrastructure layer responsible for orchestrating AI agent execution, including session state management, checkpoints, guardrails, context injection, tool execution, memory systems, model routing, and recovery mechanisms.
This is not a standard backend API engineering role. The position centers on foundational software development for production-grade AI systems, including execution engines, SDKs, orchestrators, inference optimization, reliability systems, and AI workflow infrastructure.
Mission
Design and build the execution engine and orchestration infrastructure that enables enterprise AI agents to operate safely, reliably, and efficiently at production scale.
Key Responsibilities
• Design and implement the Agent Harness shared across AI products and services
• Build agent execution engines, including graph runtime and state machine systems
• Develop internal SDKs used by engineering teams for AI agent development
• Implement session management, checkpoint systems, recovery mechanisms, long-term memory, and working memory functionality
• Build guardrail and policy execution systems to ensure safe AI agent behavior
• Design model routing systems across multiple LLM providers and model architectures
• Develop context management systems, RAG integrations, and memory infrastructure for AI agents
• Optimize inference pipelines for latency, reliability, caching, and cost efficiency
• Build workflow orchestration systems including queuing, routing, autoscaling, load balancing, and batch processing
• Collaborate with Research Engineers to productionize new AI technologies and research outcomes
• Work closely with Product Engineers, AI Quality teams, Infrastructure teams, and Data teams
• Support platform reliability initiatives, operational improvements, incident response, and post-mortem activities
• Design data access control and permission management systems for agent execution environments
Required Qualifications
• Bachelor’s degree or equivalent practical experience in Computer Science, Software Engineering, AI, Machine Learning, Mathematics, Physics, or related fields
• 5+ years of backend engineering experience
• Production development experience using Python
• Experience designing and implementing production systems utilizing LLMs or AI agents
• Experience building distributed systems, including hands-on system design and implementation
• Experience designing and implementing RESTful APIs or gRPC services
• Fluent Japanese communication skills for product and engineering discussions
• Business-level English communication skills
Preferred Qualifications
• Experience designing or implementing agent frameworks or agent harness systems such as LangChain, LangGraph, AutoGen, or similar technologies
• Cloud infrastructure experience with AWS, GCP, or Azure
• Understanding of RAG systems, vector databases, and AI memory architectures
• Experience with model routing and inference optimization
• Foundation software development experience using Go, including SDKs, runtimes, or framework development
• Deep understanding of Kubernetes and container orchestration
• Experience with event-driven architectures using Kafka, RabbitMQ, Pub/Sub, or similar technologies
• Experience implementing AI safety guardrails, policy systems, and AI observability frameworks
• Experience building ML infrastructure or MLOps environments
• Strong English technical communication skills
Technical Environment
• Backend / Infrastructure: Python, Go
• Frontend: TypeScript, React, Next.js, NX
• AI / Agent Systems: LLMs, AI agents, RAG, model routing, context injection, guardrails, memory architecture
• Agent Frameworks: LangChain, LangGraph, AutoGen
• Infrastructure: GCP, Kubernetes, Docker, Terraform
• Messaging Systems: Kafka, Pub/Sub
• Monitoring: Prometheus, Grafana, OpenTelemetry
• Interfaces: RESTful APIs, gRPC, SDKs
• AI Development Tools: Cursor, ChatGPT, Claude, Devin
Team Structure & Work Environment
• Engineering organization of approximately 120 members
• Cross-functional collaboration with Infrastructure, Data, AI, and Product Engineering teams
• Standard working hours: 10:00 – 19:00 with flexible working arrangements and negotiable core hours
• MacBook with Apple Silicon and dual monitor setup provided
Compensation & Benefits
• Annual salary: 12,000,000 – 20,000,000 JPY
• Monthly salary includes fixed overtime allowance for 45 hours
• Additional overtime paid separately
• Stock option program available
• Salary reviews and bonuses twice per year
• Full social insurance coverage
• Full transportation reimbursement
• AI tooling support including ChatGPT, Claude, Cursor, and internal AI services
• Annual development support allowance
• Book and learning support
• Language learning and certification support
• Monthly refresh allowance
• Housing allowance available for eligible areas
Hiring Process
• Application review
• Coding assessment
• 4–5 interview rounds
• Reference check before final interview
• Offer