[Hanoi] AI Native Platform Engineer

Context: Building in the AI Era

We are scaling product development alongside the evolution of generative AI. In this role you own the platform, the quality bar, and the production path so AI-accelerated delivery stays safe, scalable, and compliant for B2B back-office domains (e.g., accounting, HR) and regulated workloads. You operate in a paradigm shift toward meta-engineering: reviewing, hardening, and steering AI-assisted output, and dedicating your craft to what senior engineers must still own in production—architecture, security, reliability, and customer trust.

About the role

The guardian of production quality for AI-accelerated delivery. UI and feature “how” will increasingly be shaped by AI Product Builders and AI; this role ensures that what reaches real users is resilient, secure, and operable— especially under high concurrency, financial/HR-class compliance, and complex legacy data and services.

You delegate repetitive implementation to AI where it fits, and focus on architecture, hardening, review, and platform—meta-engineering at scale.

Responsibilities

• Advanced code review, refactoring, and safe integration of prototypes and AI-generated code into production paths.
• Scalable backend and data design: high traffic, large-scale processing, strong consistency where the domain demands it, and evolutionary service boundaries.
• AI-assisted legacy work: use AI to navigate and improve large codebases, reduce technical debt, and accelerate microservices and modularisation where appropriate.
• Security and compliance for SaaS handling financial and HR data (identity, encryption, audit, data handling).
• CI/CD, automated testing, and LLMOps so AI Product Builders can experiment safely with guardrails and promotion standards.

Requirements 

Platform and engineering depth (from ERP / platform practice)

• 7+ years building and operating web applications in production, with a platform bias: APIs, microservices, distributed systems, and reliability under load.
• Platforms and internal capabilities: experience building or operating platforms, internal tools, SDKs, or shared infrastructure consumed by other teams.
• Cloud and operations: AWS (preferred), Docker, Kubernetes, Infrastructure as Code (e.g. Terraform, K8s manifests, or equivalent).
• API design: REST and streaming where needed; developer experience, versioning, and reliability as first-class concerns.
• LLM integration in production: experience wiring LLM APIs (e.g. OpenAI, Gemini, Anthropic) into real systems, with attention to failure modes, cost, and safety.
• End-to-end ownership: design through rollout; clear decision-making and stakeholder communication; mentoring and technical design leadership.
• AI-assisted development in daily workflow; LLMOps and automation for model-related pipelines where applicable.

Required experience and skills (must have)

• Generative AI: Enthusiastic, daily use of generative AI and advanced AI tooling to streamline work and materially accelerate delivery—while remaining accountable for quality and fit-for-purpose output in production-leaning systems.
• Product mindset: Proven track record translating high-level product requirements into detailed requirements and comprehensive technical requirements through close partnership with Product Managers and domain stakeholders.
• Communication: Strong verbal and written English for clarity and alignment in distributed, multinational product engineering teams.
• Large-scale B2B SaaS (especially back-office), backend, and cloud—design and operations, not only greenfield coding.
• Complex domain models, database design, and distributed-system thinking (consistency, idempotency, backpressure, failure domains).
• Elite code review and refactoring to raise maintainability and robustness of existing and AI-generated code.
• Willingness to lead the shift toward reviewing and steering AI output rather than only writing every line from scratch.

Preferred (nice to have)

• SRE practices; observability (e.g. Datadog, logging, tracing).
• Multi-tenant SaaS or developer platforms.
• Enterprise security depth: authN/authZ, encryption, threat models for SaaS.
• Generative AI in production: prompt injection and other AI-specific controls; AI agent patterns (tool use, function calling, memory, multi-turn guardrails).
• Cross-team work with product and security; CI/CD and infrastructure automation at org scale.
• Japanese language skills (not required) — a strong plus for collaboration with Japan-based teams, product, and stakeholders.