AI Tech Lead (Context & Harness), CTO Office

必須

• Context engineering skills

  • RAG and retrieval pipelines: Experience designing advanced search and retrieval systems that provide models with accurate, relevant, and timely information.
  • Context-window and token management: Experience compressing conversation history, prioritizing useful context, and filtering noise to optimize model attention and cost.
  • Memory architecture: Experience building short-term and persistent memory systems that allow agents to retain state across tasks and interactions.
  • Instruction curation: Experience structuring plain-English operating rules, Markdown files, domain guides, and other instructions for dynamic injection into agent tasks.
  • Context formats and knowledge modeling: Experience designing context layers and reusable knowledge assets using Markdown, YAML, schemas, and related formats.

• Harness engineering skills

  • Tool and MCP integration: Experience connecting models to external APIs, execution environments, tools, and Model Context Protocol (MCP) servers.
  • Sandboxing and permissions: Experience defining safety boundaries, access controls, approval flows, and secure execution environments for agent actions.
  • Validation and guardrails: Experience implementing linters, automated tests, evaluations, and verification layers that detect hallucinations, policy violations, or broken code.
  • Orchestration and control loops: Experience designing multi-step workflows, retry logic, state transitions, and error-correction loops for long-horizon tasks.
  • Evaluation harnesses: Experience building fixtures, benchmark tasks, quality gates, and CI-integrated evaluations using DeepEval, Promptfoo, or comparable frameworks.

• Language Requirements

  • English: Business Level (Fluent, capable of handling communication with clients in English)
  • For those without a TOEIC 700+ equivalent score, they will be asked to take a designated test during the interview process (generally after the first interview)
  • Japanese: N3 Level (Able to communicate internally using translation tools for text and conversation)

歓迎

• Supporting technical and leadership skills

  • LLM and agent fundamentals: Strong understanding of agent workflows, RAG, evaluation methods, and quality gates for AI-generated output.
  • Software engineering: Strong Git/GitHub and CI practices, experience with repo-native tooling, and the ability to prototype quickly.
  • Technical leadership: Ability to make pragmatic architecture decisions, lead POCs, and turn evidence into reusable standards.
  • Communication: Ability to write clear technical proposals and provide constructive cross-team review and feedback.
  • Experience with ontology or knowledge modeling using YAML-based schemas.
  • Familiarity with internal or external agent platforms.
  • Experience with hybrid search, indexing pipelines, or context freshness mechanisms.
  • Experience in AI development and/or experience in using AI tools to improve development processes.

求める人物像

• Someone who enjoys creating standards and best practices in emerging technical domains by proactively getting hands-on.
• Someone who can balance experimentation and production readiness, always considering real-world product and workflow integration.
• Someone who actively shares findings and learnings with others and contributes to raising the collective level of the team.
• Someone who can evaluate both the opportunities and risks of new technologies, making decisions based on user value and business impact.

応募について

• If you have other qualifications or experiences demonstrating English proficiency, such as EIKEN Pre-1, EIKEN 2nd Grade (CSE score 1950+), TOEFL iBT 60+, IELTS 5.0+, or Cambridge FCE.), feel free to discuss with us

使用ツール

Overview

• Money Forward has positioned AI agents as a key part of its mid- to long-term strategy for improving operational efficiency and enhancing product value. A robust foundation for context engineering and a safe, extensible harness (execution and evaluation framework) is essential to realize this vision across multiple products and divisions.
• The number of cross-functional pilot projects is growing, and we are looking for a Tech Lead who can drive technical decision-making and build highly reusable, standardized solutions. In this role, you will translate our AI strategy into practical implementations and lead the design and delivery of a production-ready agent platform.

Responsibilities and Duties

• Lead the technical design and end-to-end delivery of the assigned “Context” and “Harness” workstreams.
• Review context formats, ontology models, harness proposals, and integration approaches, and provide constructive feedback and improvements.
• Support pilot teams across MFBS divisions with context conversion, fixture authoring, and evaluation design and execution.
• Define how content from GitHub, Notion, Slack, and other internal tools is mapped into the agent context engine.
• Establish guidelines for federated context routing and token-budget allocation across multiple sources to ensure efficient and high-quality context supply.
• Design and implement an ontology proof of concept for a specific domain and workflow using YAML-based schemas.
• Validate integration with internal or external agent platforms, including access control checks and smoke testing.
• Capture evidence and lessons learned from pilots, and contribute to a set of standards and company-wide best practices documentation.

Job Satisfaction and Experience Gained

• In this position, you will lead the core areas of “context” and “harness” for AI agents, directly contributing to the AI foundation that will support the entire organization. Rather than focusing on a single product, you will work across multiple businesses and teams, gaining experience in architecture design and standardization at an organizational scale.
• You will have many opportunities to work hands-on with state-of-the-art RAG techniques, agent frameworks, and evaluation tools, building systems that can withstand real-world production use.
• Through decision-making and cross-functional coordination as a technical leader, you will grow into an engineer who is strong in both product and technology.

Expected Role

• As an AI Tech Lead, you will go beyond implementation and define the direction for context and harness design, establishing them as shared foundations and standards within the company.
• You will own the full lifecycle from requirements clarification for pilot projects to PoC design, evaluation, and standardization, turning successful patterns into reusable templates and guidelines. You will act as a bridge between product teams, security, infrastructure, and business stakeholders to deliver balanced architectures that work in practice.
• We expect you to propose and execute realistic yet ambitious solutions while carefully weighing technical risk and cost.

Tools Used

• Repository Management ：GitHub
• CI/CD：GitHub Actions (for integration with evaluation harnesses)
• Communication ：Slack, Notion