Senior AI Software Engineer (Agentic Engineering)

AICS (ASUS Intelligent Cloud Services) is on a mission to transform healthcare through AI. We are building the next generation of Smart Hospital Information Systems (Smart HIS)—a product that demands the highest engineering standards within one of the world’s most clinically complex domains. To meet this challenge, we are embedding AI deeply into the software development process itself.

We are looking for a Senior AI Software Engineer to pioneer Agentic Engineering within our organization. You will design and implement a purpose-built knowledge extraction and Multi-Agent collaboration framework from scratch—enabling AI agents to become genuine participants in the software development lifecycle. From distilling institutional knowledge out of our codebase, to assisting in architecture design, automated code generation and validation, deep Bug Retrospectives, and closing the feedback loop—your work will fundamentally reshape how we build healthcare information systems.

What You’ll Do

Multi-Agent Architecture Design & Implementation: Architect a Multi-Agent collaboration system from the ground up, defining inter-agent state management, domain knowledge access mechanisms, and behavioral conventions (Conventions). Establish foundational agent reflection mechanisms (Reflections) and standard operating templates, and drive core proof-of-concept (POC) development through to iterative production deployment.
LLM Framework & Routing Integration: Evaluate and adopt the most suitable AI development toolkits for our stack. Implement and maintain routing tools such as LiteLLM to unify our internal multi-model API call architecture—optimizing for token efficiency, response latency, and high availability.
Context Engineering: Design and optimize RAG pipelines and knowledge extraction workflows tailored to our existing codebase and technical documentation, ensuring AI outputs remain accurate, grounded, and low-hallucination within the highly specialized business context of medical systems.
Frontier AI Architecture Validation & Operationalization: Continuously benchmark emerging AI paradigms—including Recursive Agent Architecture, Agent SKILL frameworks, and MCP—and translate the most promising into tangible engineering tools that elevate team-wide productivity.

Qualifications:

5+ years of software development experience with strong Python engineering fundamentals.
Proficiency in at least one of: Claude Code, OpenAI Codex, or GitHub Copilot.
Strong Software Architecture Design skills, with the ability to clearly articulate and plan the underlying logic of complex systems.
Hands-on production experience with LLM integration frameworks and routing tools; proficiency in LangChain, Google Agent Development Kit (ADK), or LiteLLM is required.
Solid expertise in Context Engineering, with practical experience building LLM prompt pipelines or RAG architectures.
A hacker’s mindset for hard problems—energized by unknown technical bottlenecks and able to systematically break them down.
Exceptional clarity of logical thinking, with the ability to explain complex architectures to non-technical stakeholders in plain language.

Nice to Have:

Hands-on experience with Kubernetes (K8s) containerized deployments, microservice architecture, and Linux system administration
Solid foundations in networking and low-level infrastructure knowledge.
Proficiency in JavaScript / Vue.js for rapidly building frontend validation prototypes.

What We Offer

You will not be working alone. AICS provides ample GCP and Azure cloud compute resources alongside access to leading commercial model APIs. We foster a culture of openness and technical ambition—fully supporting your exploration at the frontier of applied AI.