AI Solution Architect

Acer's AI Business Unit is seeking a visionary and technically adept AI Solution Architect to lead the design, implementation, and operationalization of next-generation AI platforms and multi-agent systems. This role is responsible for building and governing GPU-based LLM infrastructures, secure AI Gateway layers, and orchestrated multi-agent collaboration frameworks. You will work closely with AI researchers, software engineers, and infrastructure teams to architect scalable, secure, and high-performance AI systems that integrate LLMOps, RAG pipelines, and governance frameworks for enterprise use.

In addition, the AI Solution Architect will meet with customers to analyze their needs and requirements, and rapidly deliver complete, end-to-end AI application solutions.

Why Join Acer AI Business Unit?

· At Acer, we are building the future of intelligent computing by combining cutting-edge AI research, world-class hardware innovation, and global software talent.

· Joining Acer's AI Business Unit means being part of a team that transforms ideas into scalable AI platforms, products, and enterprise solutions that serve customers worldwide.

· You will collaborate with top AI engineers, researchers, and architects to design intelligent systems that power next-generation applications across LLM, multi-agent systems, secure AI gateways, and RAG pipelines.

· Most importantly, you will directly work with world-advanced workstation-level and server-level hardware platforms, gaining hands-on experience with GPU clusters, AI servers, and edge devices that drive the industry's AI infrastructure forward.

Key Responsibilities

· Design and manage GPU-powered LLM inference platforms (e.g., vLLM, Triton) on Kubernetes with CI/CD, observability, and performance optimization.

· Architect and deploy AI Gateway layers for secure, efficient, and fault-tolerant model and tool access with full governance and telemetry.

· Develop and maintain MCP (Model Context Protocol) servers, including JSON-RPC context negotiation, tool definitions, and session orchestration.

· Build and orchestrate multi-agent collaboration frameworks to coordinate context exchange, tool usage, and shared memory.

· Design and implement Retrieval-Augmented Generation (RAG) pipelines using vector databases (e.g., FAISS, Qdrant, Chroma).

· Establish and maintain LLMOps/MLOps best practices, covering model versioning, GPU utilization, deployment pipelines, and system observability (e.g., OpenTelemetry).

· Integrate enterprise authentication mechanisms (PUF-based security) and enforce security governance and access control policies across Gateway and agent layers.

· Collaborate with AI, infrastructure, and product teams to align architecture designs with business goals and performance targets.

· Engage with customers directly to analyze business requirements, system design goals, and security needs, providing complete AI solution architecture — from data pipelines, algorithms, backend APIs, MCP workflows, CI/CD automation, to secured maintenance and continuous improvement.

Required:

1. Education:

l Bachelor's degree or above in Computer Science, Information Management, Electronic Engineering, Electrical Engineering, Information Engineering, or related fields.

1. Experience:

l 1+ years of experience in AI system design, software architecture, or large-scale infrastructure deployment.

l 1+ years of practical experience in AI platform development, backend API architecture, or full-stack software engineering.

l Proven experience designing and implementing LLM inference systems, AI gateways, or multi-agent architectures.

l Hands-on experience with GPU orchestration, containerized environments (Docker, Kubernetes), and cloud platforms (Azure, AWS, or GCP).

1. Skills:

Core Skills

· Proficient in Python; familiarity with Go, C++, or TypeScript is a plus.

· Strong understanding of MLOps/LLMOps concepts, including versioning, deployment automation, and observability.

· Experience building microservices, APIs, and secure distributed architectures (REST, gRPC, JSON-RPC).

· Knowledge of vector databases (FAISS, Qdrant, Milvus, Chroma) and RAG workflows.

· Hands-on experience with Kubernetes, Docker, Helm, and CI/CD tools (GitLab, ArgoCD, Jenkins).

· Strong system debugging, performance tuning, and infrastructure monitoring skills.

Preferred:

· Experience developing AI Gateway systems, including rate limiting, token routing, fallback, and logging.

· Familiarity with MCP (Model Context Protocol) implementation and multi-agent coordination.

· Knowledge of security governance, prompt injection mitigation, and context-level access control.

· Strong problem-solving, debugging, and cross-functional collaboration skills.

· Passionate about learning new technologies and contributing to open-source AI frameworks.

· Effective communication in English and Chinese (English reading – proficient; listening/speaking /writing – intermediate).

· Excellent communication and leadership skills with the ability to bridge AI R&D and engineering teams.