About this role
About MicoAI
Mico's mission is Empower every brand by building lifetime trust through humanlike technology , and our vision is to be the Asia No.1 Brand Empowerment Company .
MicoAI is Mico's top product priority: marketers set the goal, and AI agents plan, build and run the campaigns. The first product is a chat copilot inside Mico Engage (ME), Japan's leading LINE CRM. A Customer Executive (CE) describes an e-commerce campaign in plain language, such as restock, cart abandonment or catalog recommendation. MicoAI reads the client's real data, drafts the segment, message and action, and shows a review card. Nothing is written to ME until the CE approves.
The thesis is Author → Approver : the CE stops building campaigns from a blank screen and approves complete, evidence-backed proposals. Every proposal stores why it exists, what it rejected and how confident it is.
Where we are:
- Built: chat inside ME with no second login, reads of the client's ME data, and approved writes of segments, messages, scheduled and event-triggered actions, behind a code-enforced approval gate.
- Now: taking the MVP to production for internal EC CEs, then making EC setup easy (Nov–Dec 2026).
- 2027: client setup inside MicoAI, onboarding flows, more channels (SMS, Email, Mico Voice) and recommending the next campaign. The agent is being split into a reusable Core plus one package per product, so Mico Voice can reuse it.
Required qualifications
Experience
- 5+ years of software engineering, with substantial time owning production systems on AWS, including on-call.
Skills
- Strong AWS in production: ECS Fargate, RDS / Aurora MySQL, ElastiCache (Redis / Valkey), ALB, VPC networking and IAM.
- Terraform: reusable modules, multiple environments and accounts, safe changes.
- CI/CD with GitHub Actions and Docker, including environment promotion and rollback.
- Observability and operations: CloudWatch or similar, alarm design, on-call, incident response and RCA.
- Strong TypeScript and Node.js on the backend (Fastify, NestJS or similar), and working React on the frontend.
- Cost awareness: has measured and reduced cloud cost.
- Security basics: secrets management, least-privilege IAM, web application security.
- Test-driven habits: defines a change by its tests and treats AI-written code as untrusted until verified.
- Clear written English. The team is cross-border and async-first.
Education
- A Bachelor's or higher in Computer Science or a related field, or equivalent experience.
Nice to have
- 2+ years of production work on LLM-based products or agents (tool calling, streaming, evals).
- Experience with Mastra, the Vercel AI SDK UI message stream, or MCP servers and clients.
- gRPC services and cross-account AWS PrivateLink.
- AWS WAF, CloudWatch metric filters / Contributor Insights, AWS Chatbot to Slack.
- Token-cost tracking and model routing (cheap models for classification, strong models for reasoning).
- Durable or resumable runs and idempotent write paths (approval keys, outcome-unknown handling).
- Marketing tech, CRM messaging (LINE, SMS) or e-commerce.
- Mentoring engineers, or working in a cross-border team with Japan.
Note - We are looking for someone who has FullStack developer skill with hands on in deployment.
Perks
- Competitive Salary
- Hybrid work culture
- 12 additional WFH
- Flexible vacation.
- Flexible work times.
- Health Insurance