Senior Software Engineer, Agentic AI Platform - Mercari

Work Responsibilities

You will be responsible for designing, developing, and operating the technical foundations that enable AI adoption across Mercari Group.

• Design, develop, and operate the AI Platform: Design, implement, and operate shared AI infrastructure such as the LLM Gateway, MCP Gateway, and Agent Sandbox. These are production services the whole company depends on, so you own their operation—availability, security, and cost optimization—alongside the enablement work. Decide what to offer as company-wide infrastructure by weighing the range of teams affected, the impact on development as a whole, and system-wide risk.
• Build AI Agents and an execution platform: Develop AI Agents that work alongside development and operations, and build an execution platform that shifts the developer experience toward AI-native. Design on the premise that both humans and AI Agents are users: clear interfaces, documentation and metadata prepared in a form AI can interpret, guardrails implemented as code, and mechanisms that continuously evaluate quality.
• Own adoption and outcomes: Continuously measure whether the foundations you shipped are actually being used and how the development process changed for the people using them, and when adoption does not spread, identify the cause and see the improvement through.
• Promote company-wide AI adoption: Partner with business and product teams to embed AI-first workflows across the organization through AI SaaS PoCs and community operations. Operate company-wide shared repositories as innersource, responding continuously to pull requests from other teams.

---

Development Environment

• Infrastructure: Google Cloud Platform
• Languages: Go, TypeScript, Python, etc.
• Code management: GitHub
• Configuration management: Terraform
• Analytics: BigQuery / Looker
• Knowledge: Notion, Confluence, Linear
• AI development tools: Claude Code, Codex, Cursor, etc.
• AI/LLM development: Foundation model APIs, LiteLLM, etc.

Note: Technologies may differ depending on the area of responsibility.

---

Unique Challenges

• Enable every role at Mercari to work AI-natively: Enabling thousands of engineers, designers, and PMs to make AI a baseline skill, by building the shared foundations they build on top of and the agents they use in their daily work. Your impact is measured by what those teams became able to do without you in the room, not by the number of tools you shipped. You will work at a scale where you redefine how development is done across Mercari Group, not merely provide tools.
• Implement and operate a rapidly evolving AI tech stack at Mercari scale: Tackle advanced technical challenges by operating emerging stacks such as LiteLLM, MCP, and AI Agents safely and scalably in an organization of thousands—an initiative that is globally pioneering.
• Design foundations for the agent era: Design infrastructure, architecture, and operating models from scratch for a future where humans and AI agents collaborate, and build knowledge ahead of the industry. A rough edge that a person working by hand would simply overlook becomes a large difference in failure rate once AI Agents repeat the same steps at volume. Designing with that difference built in is territory where no established answer exists yet, inside or outside the company.
• Evolve the platform through collaboration with diverse stakeholders: Work with various internal organizations (Platform, Product, Security, etc.) to lead technology selection, standardization, and adoption.
• Develop and roll out services for internal developers: You can lead everything end-to-end—from planning internal services for Mercari engineers to supporting adoption. Rather than being only a "supporter," you are expected to proactively identify and solve problems as the person who best understands internal developers' pain points. Instead of answering requests one by one, or writing guidelines and calling it done, you own the whole loop: finding the problem that keeps recurring, turning it into a reusable mechanism, driving adoption, measuring what changed, and improving on it. That also means judging what is worth turning into a mechanism at all—weighing how many teams it affects, the critical path, and system-wide risk—and declining, with your reasoning, requests that cost a lot and help only one team. This role is not a reactive support desk that measures itself on response time, and not a gatekeeper that uses standards as a means of control.
• Work as a user of the platform you build: Use your own foundations in your own daily development, and join the teams that use them to understand their problems firsthand. Rather than imposing standards and processes as constraints, you can aim for a state where they get chosen because they are the faster way to get the work done.

---

Qualifications

Required Experience/Skills

• Empathy with Mercari Group and each company's mission and values
• Experience designing, developing, and operating backend or platform/infrastructure systems for large-scale web services
• Production experience building applications with one of Go, TypeScript, Python, etc.
• Experience developing/operating managed services or SDKs for internal developers and improving developer productivity
• Experience designing and operating infrastructure on cloud platforms such as Google Cloud Platform (including Kubernetes, Terraform, etc.)
• Experience designing and implementing applications or platforms using Generative AI / LLMs
• Strong communication skills to collaborate with multiple stakeholders, lead technical decision-making, and drive projects forward
• Experience acting as the owner of technical quality in your area, making the case for medium- to long-term investments such as architecture, standards, and shared foundations in business terms, and driving them forward
• Ability to form hypotheses and make autonomous decisions in uncertain situations and execute effectively
• Someone who incorporates AI into their daily development work and reviews its output with their own judgment rather than taking it at face value

Preferred Experience/Skills

• Experience developing/operating AI platforms such as MCP Servers, AI Agents, and AI agent execution environments
• Experience designing interfaces and implementing guardrails on the premise that AI Agents operate autonomously
• Experience designing evaluation methodologies for AI agents/LLM applications (e.g., defining evaluation criteria, building benchmarks, quantitatively validating quality through A/B tests, etc.)
• Experience improving development processes / harness engineering using AI development tools (Claude Code, Codex, Cursor, etc.)
• Hands-on experience in Developer Productivity / Platform Engineering / SRE
• OSS contributions and community activity experience

Language

• English: Independent (CEFR - B2) (required)
• Japanese: Independent (CEFR - B2) (optional)