AI Agent Engineer
Summary
Design, build, and optimize domain-specific AI agents (e.g., for semiconductor design/manufacturing and internet products) end-to-end, from architecture and tool/API integration to evaluation and iteration. Core stack: LLMs, RAG pipelines, orchestration frameworks like LangChain/LlamaIndex, and Python.
About the role
Design, build, and optimize domain-specific AI agents across multiple areas such as semiconductor design, semiconductor manufacturing, and internet products. 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
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
About you
Strong understanding of agentic systems, including planning, reasoning, memory, tool use, and reflection mechanisms
Experience designing modular, scalable, and maintainable agent architectures for domain-specific applications
Hands-on experience with commercial and open-source LLMs
Proficiency in prompt engineering, chaining, and policy design to guide agent behavior
Expertise in building RAG pipelines: document ingestion, embedding, vector search, context fusion, and answer generation
Ability to optimize retrieval relevance and mitigate hallucination in domain contexts (e.g., semiconductor or internet product data)
Skilled at connecting agents to external tools, databases, and enterprise APIs
Experience with agent orchestration platforms such as LangChain, LlamaIndex, Semantic Kernel, or custom frameworks
Capable of designing robust evaluation strategies and data-driven mindset for continuous agent improvement and A/B testing
Solid coding skills in Python
