English summary for screening — check the original posting before applying.
Join a new AI development team as an early member and lead the development and architecture design of AI products using LLMs. This role involves building scalable systems for production environments, not just technical verification.
Must-haves
- 3+ years of backend web application development experience (Go, TypeScript, Python, Ruby, etc. accepted)
- Experience designing and implementing RESTful API or GraphQL
- Experience designing and operating RDBMS/NoSQL databases
- Experience developing with public cloud platforms (AWS, GCP, etc.)
- Strong interest in the technical mechanisms of Generative AI (Claude, Gemini, Github Copilot, Cursor, ChatGPT, etc.)
Nice-to-haves
- Experience developing/operating applications using LLM APIs (Anthropic, Google Gemini, OpenAI, etc.)
- Experience implementing with AI frameworks like LangChain, LlamaIndex
- Experience building RAG systems, or operating search engines/vector databases
- Experience designing/developing microservices architecture or distributed systems
- Experience with IaC using Docker/container technologies, Terraform, etc.
Tech stack
PythonGoTypeScriptAWSGCPDockerTerraformOpenAI APIClaudeGeminiLangChainLlamaIndex
Work style
Onsite in Tokyo (Shibuya-ku). Flexible start time between 9:30 and 11:00.
Other notes
Annual salary range: 5,500,000 JPY - 7,000,000 JPY. Special bonus system.