AI Architect (內湖瑞光總部)
Advantech Co., Ltd.11 hours ago
Taipei, TaiwanSenior / Staff+
Responsibilities
- Define and own the end-to-end architecture for enterprise AI agents and applications across model, skill/MCP, data, and integration layers.
- Architect the NemoClaw model platform, including evaluation, benchmarking, fine-tuning, model routing, harness engineering, and inference optimization.
- Design the enterprise skill registry, MCP server framework, agent orchestration, and A2A standards with reuse and versioning governance.
- Establish data and RAG architecture covering semantic layers, master data, vector stores, knowledge bases, and retrieval pipelines.
- Set standards for secure on-premises and data-isolated deployment, RBAC, audit trails, prompt-injection defense, guardrails, and responsible-AI reviews.
- Design secure integration patterns for agents to interact with enterprise systems through governed APIs, data, and permissions.
- Define agent CI/CD, tracing, telemetry, regression testing, token-cost management, and capacity practices.
- Create reusable architecture patterns, implementation templates, and guardrails; conduct design and code reviews and mentor engineers.
- Evaluate frontier models, agent frameworks, RAG stacks, and emerging protocols, and make build-versus-buy and platform-direction recommendations.
- Prototype, review implementations, and partner with AI engineers and the AI Project Manager to deliver adopted production solutions.
- Ensure the platform meets performance, reliability, scalability, and cost targets across business domains.
- Provide architectural guidance for broader enterprise application and system-integration projects when needed.
Requirements
- 7–12 years of experience in software engineering, AI/ML, data engineering, or solution architecture, including 3+ years designing production AI/ML or large-scale distributed systems.
- Proven experience designing and shipping production systems using LLMs and agentic architectures, including RAG, tool use, and orchestration.
- Deep hands-on expertise with models and inference, prompt and harness engineering, vector stores and retrieval, and APIs and system integration.
- Strong software engineering fundamentals and the ability to establish architectural standards, conduct reviews, and mentor engineers.
- Experience with Azure and/or AWS and with on-premises or data-isolated deployment.
- Understanding of AI and data governance, security controls, and human-in-the-loop design.
- Ability to translate business needs into architecture and communicate technical direction to engineering and business stakeholders.
- Bachelor’s or master’s degree in Computer Science, Engineering, or a related field, or equivalent practical experience.
- Professional working proficiency in English and Mandarin Chinese.
- Preferred experience building internal AI platforms such as model gateways, MCP or skill registries, and agent orchestration frameworks.
- Preferred familiarity with SFT, LoRA, RLHF, model evaluation, benchmarking, LLM observability, eval-driven testing, token-cost management, and capacity management.
- Preferred knowledge of CRM/SFDC, e-commerce, quotation, ERP, and API-gateway design.
- Preferred exposure to the NVIDIA AI stack, on-premises GPU infrastructure, or open-source LLM serving.
- Contributions to open-source AI or agent projects, relevant publications, and cloud or AI architecture certifications are advantageous.
Categories
About Advantech Co., Ltd.
Advantech Co., Ltd. designs and sells industrial PCs, embedded boards, IoT gateways, and edge-computing platforms—plus software such as its WISE-IoT suite—for manufacturers, utilities, healthcare, transportation, and retail. The company also provides design-in and systems integration services. Founded in 1983 and headquartered in Taipei’s Neihu District, it is a public company listed in Taiwan and serves customers globally.