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 role sits within the system infrastructure development team responsible for building platforms that support enterprise AI use. The focus is an AI agent foundation that connects internal data, APIs, source code, and documentation while enabling secure and consistent business-system operations.
The engineer leads architecture and development across ontology and Knowledge Graph design, RAG integration, GraphQL gateways, REST API standardization, MCP Server connectivity, transaction control, approval and authorization flows, and update APIs for AI agents. The named stack includes Java with Spring Boot, Apache Beam, Netty and Reactor; Node.js, Python and Rust; PostgreSQL, Apache Ignite and Redis; Docker; Kafka, Flink and Solace; and JavaScript, Vue.js and TypeScript. GraphQL, WebSocket, WebRTC, SIP, Asterisk and LiveKit are also listed.
Applicants must have either backend development experience and leadership experience on large-scale business systems, including detailed design, implementation and review, or experience developing and operating backend APIs at an in-house web company together with BFF design experience.
This is an AI-generated summary of the employer's original posting — details can be incomplete, out of date or simply wrong.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.
Lead customer-specific software projects for major Japanese companies, covering requirements, architecture, data pipelines, implementation, deployment, and operations. Remote work is available.
Design and implement machine-learning algorithms using tabular, natural-language, and image data, then work with consultants and software engineers to turn client solutions into usable software.
Provide senior technical support for Red Hat Enterprise Linux in hybrid-cloud environments, resolve complex customer issues, share knowledge, and coordinate with developers and QE to improve the product.