Build AI Worker VoiceAgent’s web frontend, designing visual interfaces and admin features, selecting architecture, and delivering releases with TypeScript and React in a hybrid office/home role.
About this role
CyberAgent's AI Operation Technology team builds systems that automate and improve the group's internet advertising business, which is handled at very large scale. It hires an AI Agent Backend Engineer for Koka Omakase AI, an AI agent launched in April 2026 that continuously monitors and optimises bidding and delivery settings on major ad platforms such as Meta, Google and Yahoo!.
The engineer works from requirements to design, implementation and operational improvement, mainly in Python backend and AI-agent development. Work includes new agent features, improving existing logic, connecting agents to internal platforms, and building data pipelines for agent execution and for visualising execution logs, using Snowflake and AWS. The stack is Python and TypeScript with React, dbt, Snowflake, AWS, GitHub Actions, Datadog and Claude Code. The team is small and flat.
Applicants need five or more years of web application and API development, two or more years of Python, cloud experience on AWS or GCP, GitHub team development, Docker, unit testing, and the ability to organise vague requirements. Python for five years or more, tech lead experience, AI code agents and ad-industry basics are preferred.
This is an AI-generated summary of the employer's original posting — details can be incomplete, out of date or simply wrong.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
Advise clients on data strategy, build DWH and BI foundations, and use SQL, Python, machine learning and CRM analytics to improve marketing, forecasting and business operations.
Lead requirements definition and delivery of client-specific AI agents for advertising and marketing, coordinating stakeholders and supporting clients’ AI transformation in a hybrid Tokyo role.
Builds the data foundation for an AI and analytics product by matching records, modeling reliable datasets, and improving the quality and consistency of entertainment data.
Design data platforms, models, governance, and knowledge graphs for AI-based financial advice, including architecture, data flows, and continuous learning; remote work is possible weekly.
Learn warehouse-system implementation through configuration, data preparation and testing, then grow into customer requirements, operating design and project coordination.