AI / Machine Learning Engineer
AI Tools
Tech Stack
Agent Workflow
Design and deploy multi-modal, tool-using agents that classify inquiries, ask clarifying questions, and draft estimates using RAG pipelines and function-calling. Build vector search and knowledge graphs.
About the Role
Monoya, a well-funded Tokyo startup reinventing how manufacturing companies grow internationally, is hiring an AI/Machine Learning Engineer. The role focuses on LLM-powered agents — designing and deploying multi-modal, tool-using agents that classify inquiries, ask clarifying questions, and draft estimates using RAG pipelines and function-calling. You will build and tune vector search and knowledge graphs over Firestore + Weaviate, establish repeatable benchmarks and evaluation metrics, and convert PoCs to clean tested services on Cloud Run.
Requirements:
- 2-3 years building ML or data-intensive systems
- Clean Python proficiency
- Fluency in at least one deep-learning framework (PyTorch preferred)
- Shipped experience with modern LLM tooling (OpenAI, Ollama, vLLM, Hugging Face, LangChain, LiteLLM)
Tech stack: OpenAI, Ollama, LangChain, Firestore, Weaviate, Python FastAPI, Cloud Run, Docker, GitHub Actions, Terraform.