Leads customer implementations of LLM and generative-AI systems from architecture through production, building full-stack solutions and improving model quality.
About this role
This senior technical leadership role sits within SoftBank’s Business Systems Development organization, developing Crew Agent, an in-house generative-AI platform for store customer service. The platform consolidates AI agents that support search, recommendations, and registration tasks, with planned features including proposal-support output, voice input, and customer-information capture.
The lead defines architecture, implementation direction, technical decisions, and quality standards across BFF, frontend, backend, and AI-orchestration workflows. The work includes design reviews, code reviews, task decomposition, testing strategy, CI/CD, monitoring, and coordination with business teams, product managers, and vendors. The posting requires at least five years of web-application design, implementation, and review experience, plus three years leading development across multiple areas such as frontend, backend, infrastructure, and AI integration. Practical architecture, quality-management, and code-review experience is also required.
This is an AI-generated summary of the employer's original posting — details can be incomplete, out of date or simply wrong. Always confirm everything on the official posting before applying.
Similar jobs
Leads enterprise AI implementations from requirements to production, designing architecture, data connectivity, and RAG pipelines while guiding technical standards in a hybrid Tokyo role.
Plans and develops EMS services for homes and commercial users, integrating batteries and solar devices with web/mobile apps, cloud systems, APIs, and AI-based demand and generation forecasting.
Manage the Application Platform team supporting BUYMA development teams with backend modernization, microservices, SRE practices, cloud scalability, and AI-assisted development.
Leads customer-facing transformation projects that apply generative AI, LLMs, RAG, and AI agents to software development, from PoC planning through adoption.
Build reliable automated tests for core input systems such as internationalization, Pencil and keyboards. Investigate failures and improve testing frameworks.