🚀 We're Hiring: Agent Harness Engineer (Backend + AI Systems Engineering) | Tokyo, Japan
Ready to build the infrastructure powering the next generation of AI?
Join one of Japan's fastest-growing AI companies and help design the Agent Harness—the execution engine that enables AI agents to operate safely, efficiently, and at scale. This isn't another backend role. You'll build the core infrastructure behind enterprise AI systems used by 200+ companies and empower over 120 in-house engineers with the SDKs, orchestration, and tooling they rely on every day.
💰 Salary: ¥12,000,000 – ¥20,000,000 JPY
📍 Location: Tokyo, Japan (Hybrid)
🌏 Language: Business English accepted (No Japanese required)
🔥 What You'll Build
As an Agent Harness Engineer, you'll design and develop the execution layer that sits between large language models and enterprise applications.
Your work will include:
- Building LLM-centric execution engines and orchestration systems
- Designing Agent SDKs used across the engineering organization
- Developing guardrails and policy engines for safe AI execution
- Implementing model routing, context management, and memory architectures
- Optimizing inference pipelines for performance, scalability, and cost
- Collaborating with AI researchers to bring cutting-edge research into production
✅ Must-Have Qualifications
- Bachelor's degree (or equivalent practical experience) in Computer Science, Software Engineering, AI, Machine Learning, Mathematics, Physics, or a related field
- 5+ years of backend engineering experience
- Production development experience with Python
- Experience building production systems using LLMs or AI agents
- Strong experience designing and implementing distributed systems
- Experience developing RESTful APIs and/or gRPC services
- Business-level English communication skills
⭐ Nice-to-Have Skills
- Experience with agent frameworks such as LangChain, LangGraph, AutoGen, or similar
- Cloud platform experience (AWS, GCP, or Azure)
- Knowledge of RAG, vector databases, and AI memory architectures
- Model routing and inference optimization
- Foundation software development in Go
- Kubernetes and container orchestration
- Event-driven architectures (Kafka, RabbitMQ, Pub/Sub)
- AI safety guardrails, policy execution, and observability
- ML infrastructure and MLOps experience
🌟 Why You'll Love This Role
✅ Build an in-house Agent Harness instead of relying on open-source frameworks
✅ Work at the intersection of AI/ML, distributed systems, and backend engineering
✅ Design SDKs and developer tools used by 120+ engineers
✅ Influence the architecture behind AI products serving 200+ enterprise customers
✅ Collaborate closely with Research Engineers to bring the latest AI innovations into production
✅ Enjoy significant technical ownership in a rapidly growing AI company
If you're passionate about distributed systems, LLM infrastructure, and building the future of enterprise AI, we'd love to connect.
📩 Apply now
#Hiring #BackendEngineer #Python #AIEngineering #LLM #AgenticAI #LangChain #DistributedSystems #Kubernetes #MLOps #RAG #TokyoJobs #JapanJobs #SoftwareEngineer #ArtificialIntelligence #TechCareers #HybridWork