AI Agent Engineer - Domain-Specific, End-to-End Orchestration

Oppstar Technology; Penang; On-site; MYR 60,000 - 120,000; Full time

Job summary

Oppstar Technology is seeking an experienced engineer to design, build, and optimize domain-specific AI agents across semiconductor design, manufacturing, and internet products. You will own the end-to-end lifecycle of AI agents, including requirement discovery, agent architecture design, tool integration, and continuous iteration based on user feedback.

Key responsibilities include designing multi-step reasoning flows, integrating external tools, conducting prompt optimization, and

Qualifications

• Strong understanding of agentic systems: planning, reasoning, memory, tool use, reflection.

Responsibilities

• Design multi-step reasoning flows, integrating external tools and APIs.
• Conduct prompt and policy optimization, and implement evaluation strategies to measure task success, safety, and reliability.
• Work with LLM platforms, retrieval-augmented generation (RAG), and orchestration frameworks.
• Translate complex business and engineering use cases into practical AI agent solutions.
• Collaborate closely with domain experts to encode workflows and best practices into robust, reliable agentic systems.
• Connect agents to external tools, databases, and enterprise APIs (e.g., EDA tools in chip design, CRM, internal microservices).
• Implement multi-agent coordination and complex workflow automation.
• Design robust evaluation strategies: task success metrics, safety guardrails, reliability benchmarks, and user feedback loops.

Job description

Oppstar Technology is seeking an experienced engineer to design, build, and optimize domain-specific AI agents across semiconductor design, manufacturing, and internet products. You will own the end-to-end lifecycle of AI agents, including requirement discovery, agent architecture design, tool integration, and continuous iteration based on user feedback.

Key responsibilities include designing multi-step reasoning flows, integrating external tools, conducting prompt optimization, and