Staff AI Engineer (Lead )
Summary
Lead the design of AI agent systems that automate security workflows across the software development lifecycle, integrating LLMs, context engineering, and CI/CD tools to enforce secure coding and release governance.
We are hiring a Staff AI Engineer (Lead) to design and drive an ambitious agentic security workflows covering the full SDLC — from requirements, threat modeling, secure coding, CI/CD validation, security testing, release risk assessment, and production feedback loops.
This role focuses on building reliable AI agent systems that understand product security context, support SDLC validation, improve release readiness, and help engineering teams adopt secure AI-assisted development practices. The ideal candidate combines AI agent engineering, backend/platform experience, and cross-team technical leadership.
Why Money Forward?
- Join Money Forward at a major strategic turning point as the company shifts from “cloud” to “AI” and advances AX (AI Transformation) beyond traditional DX.
- Help build the foundation for AI agents and “digital workers” that can autonomously perform back-office tasks across Money Forward products.
- Own greenfield architecture for agentic security workflows that directly support the company’s AI strategy, product trust, and secure AI-driven development.
- Work on a rare intersection of agentic AI, application security, and cross-team engineering leadership, shaping reusable standards, guardrails, and implementation patterns across product teams.
- Contribute to Money Forward’s ambition to become Japan’s No. 1 back-office AI company by enabling safer, faster, and more reliable AI-powered value creation.
- Help shape one of the company’s most advanced agentic AI initiatives: a multi-agent security workflow designed to support the full software development lifecycle, while keeping human review, safety boundaries, and release governance in place.
Responsibilities
- Design end-to-end agentic security workflows for SDLC validation, patch management, proactive testing, risk reporting, and release gates.
- Own the product security context model, including architecture, data sensitivity, authentication/RBAC, credential and PII handling, logging touchpoints, release tier, and critical product flows.
- Define agent decision rules, including advisory behavior, human-review requirements, release-blocking criteria, risk thresholds, and escalation paths.
- Design and implement agent guardrails such as least-privilege access, prompt-injection handling, safe tool execution, audit logging, rollback, and kill-switch mechanisms.
- Build and maintain AI agent workflows using LLMs, context engineering, tool integrations, orchestration, harness design, loop engineering, and evaluation pipelines.
- Validate agent outputs with security experts before rules are trusted for production use.
- Lead application engineers across divisions and translate agentic workflow designs into stack-specific implementation patterns.
- Work with SRE/PRE on CI/CD integration, GitHub/CircleCI workflows, Datadog checks, staging safeguards, and release-gate mechanics.
- Coordinate with QA, privacy, and security specialists on regression validation, release readiness, PII handling, and secure coding rules.
- Own false-positive tuning, rule-change backlog, and continuous improvement of agent quality.
Requirements
Requirements
- Bachelor’s degree or higher in Computer Science, Software Engineering, or a related technical field.
- Strong experience with Python or JavaScript building LLM-based applications and AI agents, with hands-on experience in LLM tooling, frameworks, platforms, and evals.
- Strong understanding of context engineering, instruction design, prompt hardening, tool boundaries, harness design, loop engineering, and agent evaluation.
- Ability to design production-ready agent workflows with clear inputs, outputs, failure modes, human-review points, and escalation rules.
- Experience with CI/CD, observability, logging, monitoring, and production-readiness practices.
- Ability to lead 3–5 engineers across teams without direct authority.
- Strong problem-solving skills
- Strong communication skills
Preferred Skills and Experience
- Experience with AI agent frameworks such as LangGraph, LangChain, OpenAI Agents SDK, or equivalent.
- Experience integrating AI workflows into GitHub, CircleCI, Datadog, or similar engineering platforms.
- Experience creating reusable engineering standards, templates, checklists, and enablement materials.
- Working knowledge of application security concepts such as threat modeling, OWASP, secure coding, secrets handling, PII handling, and release risk assessment; or proven ability to work closely with security experts and convert their knowledge into agent rules and checklists.
- Working familiarity with additional stacks used across product teams, such as Ruby/Rails, Go, Java, React, or Vue.
- Ability to work effectively in a rapid, iterative development environment with a high degree of autonomy.
Language Requirements
- Japanese: Business-level or higher preferred. (Optional)
- English: Ability to read and write technical documentation and collaborate with engineering teams.