Overview
Guided by Money Forward AI Vision 2026, Money Forward is driving company-wide AX (AI Transformation) to deliver "digital workers" — AI agents that carry out business operations autonomously. The CDAO Office leads the AI and data strategy that makes this possible across the entire group.
Join the Mepar (Money Forward Engineering Productivity AI Research) team as a Staff AI Engineer and lead the design of production-grade AI agents that power customer-facing products. In this role you'll own the hardest technical problems at the intersection of agent engineering and backend/infrastructure at scale — turning fast-moving prototypes into reliable, secure, cost-efficient systems that ship to real users.
This is a hands-on, high-leverage individual-contributor role. You'll set technical direction for how we build, evaluate, deploy, and operate agentic systems — including the durable, long-running execution runtime that lets agents complete real back-office work end to end — and raise the bar for engineering across the team while writing code yourself. You'll partner closely with product, business, backend, frontend, infrastructure/SRE, and QA teams to deliver impactful, responsible AI end to end.
Responsibilities and Duties
- Agentic System Design: Architect, build, and scale multi-agent systems and LLM-powered services for customer-facing products — from prototype to production, built to sustain heavy real-world load.
- Agent Engineering: Design reliable tool-use, function-calling, memory, multi-turn, protocols and modern orchestration frameworks; establish guardrails, evaluation, and safe fallback behavior.
- Backend & Infrastructure at Scale: Own backend services, APIs, and the infrastructure that agents run on — high availability, low latency, secure secrets/credential handling, and horizontal scalability under production traffic.
- Evaluation & Benchmarking (core focus): Own how we measure agent quality. Build the evaluation harness end to end — representative task sets, fixed inputs and reference outcomes, repeatable runners, and scoring across task completion, correctness, latency, cost, and human-intervention rate. Establish LLM-as-a-judge and offline/online eval, wire evaluation into CI as a regression gate, and grow from a pilot task set to a durable benchmark suite that product and QA can trust as an acceptance gate.
- Durable & Long-Running Agent Execution: Design the runtime for agentic tasks that run for ten minutes or longer — durable task lifecycle (submit, status, timeout, cancel, complete, fail), isolated sandboxes for code and file execution, artifact generation and retrieval, and a harness for retries, back-off, checkpointing, resume, and self-recovery.
- Reliability & Cost: Identify bottlenecks; optimize latency, throughput, token/compute cost, and reliability; instrument observability across the agent lifecycle.
- Safety & Governance: Apply security and governance best practices (input validation, content filtering, PII handling, HITL escalation, risk-based sampling) appropriate for customer-facing systems.
- Cross-Functional Technical Leadership & Mentorship: Partner day-to-day with product, business, backend, frontend, infrastructure/SRE, and QA to translate business goals into agent architecture; align standards across BE/AI/Infra, drive system-level decisions that span team boundaries, and mentor engineers on agent development, LLM integration, and evaluation methodology.
Required Skills and Experience
- 7+ years of professional software engineering experience, with strong recent hands-on delivery (not purely managerial).
- Deep backend engineering expertise — designing, building, and operating large-throughput , low-latency production systems and secure APIs.
- Strong infrastructure skills: cloud ( AWS and/or Azure ), containers ( Docker ), orchestration ( Kubernetes ), Infrastructure as Code ( Terraform ), and CI/CD — including operating and troubleshooting production services.
- Proven experience building AI agents / agentic orchestration for real products, with hands-on use of modern agent frameworks — especially the Claude Agent SDK (agentic loop, tool use, sessions, sandboxed execution, Skills). Comparable depth in LangGraph or similar orchestration frameworks is relevant, as is judgment on when a single agentic loop beats a multi-stage pipeline.
- Strong command of Python or TypeScript for building production services (e.g., FastAPI / FastMCP , async request handling, dependency and lifecycle management, ASGI/Node runtimes)
- Solid understanding of MCP, REST API, GraphQL protocols for tool integration and agent-to-agent communication.
- Demonstrated experience building agent evaluation from scratch — not just consuming dashboards. You have designed task sets and scoring rubrics, run controlled baseline-versus-variant experiments, and used the results to drive architecture decisions.
- Experience with LLM tracing and observability (OpenTelemetry / OpenLLMetry, Langfuse, or equivalent) and with performance and load testing of production services.
- Experience building or operating durable / long-running execution infrastructure — job and task lifecycle management, isolated sandboxes (containers, microVMs, or managed sandbox services), artifact storage, and failure recovery.
- Strong grasp of core CS fundamentals: data structures, algorithms, software design, and engineering best practices.
Preferred Skills and Experience
- Experience shipping AI features in customer-facing / B2B SaaS products under real security and compliance constraints.
- Experience with guardrails, safety, and governance frameworks for LLM/agent systems (e.g., OWASP-style threat modeling for agents).
- Experience with cost optimization for LLM usage (context compression, model routing, non-frontier models, gateways).
- Fluent use of AI-assisted development tools (Claude Code, Cursor, GitHub Copilot, Codex) with sound judgment on when to delegate to AI and when to verify.
Language Requirements
- Japanese: Not required but nice to have
- English: Business level (equivalent to TOEIC 700 or above)
- If you do not have a qualification equivalent to TOEIC 700 or above, you may be required to take a company-designated test during the selection process.
Who We’re Looking For
- Strong interpersonal and communication skills with a track record of leading across cross-functional teams.
- Enthusiastic about mentoring and growing other engineers.
- High level of ownership and accountability, comfortable driving ambiguous, high-impact initiatives.
Work Environment
At Money Forward, we provide an environment where we can create world-class services together, and we are looking forward to welcoming you.
- Provided PC Specs: We provide PCs equipped with the latest CPUs (MacOS or Windows). Custom-made PCs tailored to business requirements and replacements with the latest OS are also possible.
- Systems to Enhance the Development Environment: Peripheral devices necessary for work (such as displays, mice, keyboards) can be purchased as office supplies. Generally, you can choose from standard products (catalog), and if conditions are met, you can apply for non-standard products as well.
- Money Forward Library: We have a library system where you can freely borrow books, ranging from technical books to management books. Desired books can be purchased at the company's expense.
- Referral Driven: We cover the cost of recruitment meals. There is a referral reward system.
- Conference Participation Support: The company partially covers participation in domestic and international conferences, such as RubyKaigi and Google I/O.
| 職種 / 募集ポジション | Staff AI Engineer (AI Agents Development), CDAO Office, Tokyo |
|---|---|
| 雇用形態 | 正社員 |
| 給与 |
|
| 勤務地 | |
| Salary System | <Salary Range> Min 917,000 JPY / month（11,004,000 JPY / year）- 1,667,000 JPY / month（20,004,000 JPY / year） Each including fixed allowances of 266,988 JPY - 485,282 JPY / month. |
| Bonus | A「High Performance Bonus」may be paid to employees who receive high evaluations based on semi-annual evaluations in addition to their salary. ※Please note that the remuneration of the High Performance Bonus is subject to change according to the company's performance. |
| Probation Period | 3 months from join date |
| Working Hour System | Discretionary Labor System for Professional Work ※Conditions apply; subject to change to Flextime System. |
| Working Hours | 9:30 - 18:30 (60 min break) are the basic working hours. However, employees are able to choose their working hours at their own discretion. ※There is potential for overtime work outside the determined hours. |
| Work Style Policy | Hybrid work style ・As a standard practice, employees are required to work at the office a minimum of 2 days per week. Employees are encouraged to spend 3 or more days in the office. (This policy may be subject to change based on the company and job circumstances) ・The specific "team office days" may vary depending on the assigned team. |
| Holidays/Vacations | ■ Saturdays / Sundays / Japanese national holidays ■ Paid holidays ■ Summer holidays (3 days) ■ Winter holidays (2 days) ■ Year-end and New Year’s holidays (Dec 31st～Jan 3rd) |
| Benefits | ■ Various social insurances (employee pension, health insurance, employment insurance, industrial accident compensation insurance) ■ Neighborhood housing allowance and neighborhood moving allowance ■ Health check and gynecological checkup ■ Influenza vaccine ■ Book purchases support ■ Defined-contribution corporate pension ■ Employee stock ownership plan ■ Preferential treatment when using the following services（limited to businesses under contract with Money Forward） - Rental agency - Housekeeping services - Babysitting - Online English conversation school |
| Selection Process１ | Casual interview/Document Screening ↓ First interview (Depending on the position, there may be a technical assignment before the interview.) ↓ Several interviews (The number of interviews depends on the position. We will request you to take an aptitude assessment.) ↓ Final interview (We may ask for a reference check before or after the interview.) ↓ Job offer/Offer meeting ※The process may be subject to change depending on the case. |
| Selection Process２ | ■ About the Aptitude Test It is a simple web-based survey taking around 20 minutes to complete. ■ What are reference checks? Money Forward may ask for your cooperation with reference checks using a reference check service tool. We believe that mutual understanding is limited to the selection process alone. Therefore, we would like to gather information about you from your supervisor and colleagues at your current or former company to ensure a more reliable match and facilitate your early success after joining our company. ※We do not make employment decisions based solely on the contents of reference checks. ※The fact that you are in the selection process with us will not be disclosed to referees. |
| Notes | - Range of change in job description: Work as determined by the company - Range of change in work location: Work location as determined by the company |
| Reference Information | https://recruit.moneyforward.com/#introduction |
| 会社名 | 株式会社マネーフォワード |
|---|---|
| 代表者 | 代表取締役社長グループCEO 辻 庸介 |
| 創業 | 2012年5月 |
| 取締役 | 金坂 直哉 中出 匠哉 竹田 正信 石原 千亜希 |
| 社外取締役 | 安武 弘晃 宮澤 弦 Ryu Kawano Suliawan 菊間 千乃 芦田 健 上田 梨々子 |
| 監査役 | 畠山 優実 田中 克幸 西山 茂 |
| グループCxO・VPox | 上利 陽太郎 瀧 俊雄 山田 一也 坂 裕和 松岡 俊 伊藤 セルジオ 大輔 関田 雅和 松久 正幸 野村 一仁 長尾 祐美子 金井 恵子 梅田 康吉 丸山 嘉伸 |
| 執行役員 | 田平 公伸 本川 大輔 冨山 直道 永井 博 駒口 哲也 廣原 亜樹 島村 誠一郎 永井 七奈 木村 慎治 吉本 憲文 工藤 裕之 島内 広史 小山 幸宏 渡辺 恵伍 松村 道夫 岩崎 大 渋谷 亮 |
| オフィス | 本社オフィス 〒108-0023 東京都港区芝浦3-1-21 msb Tamachi 田町ステーションタワーS 21F 北海道支社 〒060-0061 北海道札幌市中央区南一条西4-5-1 札幌大手町ビル3階 東北支社 〒980-0021 宮城県仙台市青葉区中央2-2-10 仙都会館 5F 東海支社、名古屋開発拠点 〒450-6213 愛知県名古屋市中村区名駅4-7-1 ミッドランドスクエア 13F 京都支社、京都開発拠点 〒604-8004 京都府京都市中京区三条通河原町東入中島町78番地 明治屋京都ビル 4階 関西支社、大阪開発拠点 〒541-0042 大阪府大阪市中央区今橋 2-5-8 トレードピア淀屋橋 9階 広島支社 〒730-0015 広島市中区橋本町9-7 ビル博丈5F 九州・沖縄支社、福岡開発拠点 〒810-0041 福岡県福岡市中央区大名2丁目6-50 福岡大名ガーデンシティ 16F |
| 社内コミュニケーション活性化の取り組み | ■全社週次/月次朝会/半期総会 ■代表との意見交換会（CEOセッション） ■全社懇親会（MF Happy Hour） ■他部門社員との交流会（シャッフルランチ・ディナー） ■上長との定期1on1（ツキイチ面談） ■社内公募制度（MFチャレンジシステム） ■社員満足度調査（MFグループサーベイ） ※一部正社員のみ |
| 労働条件 | 屋内原則禁煙（喫煙室あり）等 |
| 中途採用比率 | 2021年11月末 93.8％ 2022年11月末 90.0% 2023年11月末 76.6％ 2024年11月末 88.7% |