Senior Agent AI Engineer

Senior Agent AI Engineer

A job at TSMC Arizona offers an opportunity to work at the most advanced semiconductor fab in the United States. TSMC Arizona’s first fab will operate its leading-edge semiconductor process technology (N4 process), starting production in the first half of 2025. The second fab will utilize its leading-edge N3 and N2 process technology and be operational in 2028. The recently announced third fab will manufacture chips using 2nm or even more advanced process technology, with production starting by the end of the decade. America’s leading technology companies are ready to rely on TSMC Arizona for the next generations of chips that will power the digital future.

 

As a Senior Agent AI Engineer, you will design and build autonomous agents capable of reasoning, decision-making, and interacting with external systems (APIs, databases, external tools). You will work on building systems that enable agents to autonomously carry out tasks, plan actions, and collaborate with other agents, ensuring that these agents behave in a safe, reliable, and ethical manner. You will leverage cutting-edge AI technologies to design and implement autonomous agent systems that extend the capabilities of language models (LLMs) through integration with APIs, tools, and external software environments. You will focus on enabling agents to act independently, collaborate in multi-agent systems, and execute tasks with safety, reliability, and ethical considerations.

Key Responsibilities:

• Design and implement autonomous agent systems with a focus on behavior modeling, task execution, and collaboration.
• Integrate language models (LLMs) with tools, APIs, and software environments to extend agents’ capabilities, such as interacting with databases, browsers, or external tools.
• Develop agent memory systems, task tracking mechanisms, and goal-directed behaviors to enable agents to act autonomously in dynamic environments.
• Implement multi-agent systems to allow agents to collaborate, share knowledge, and solve complex problems collectively.
• Ensure agents' actions align with predefined ethical and safety constraints, minimizing risks and unwanted behaviors.
• Test and evaluate agents in real-world scenarios, iterating on designs based on feedback and performance metrics.
• Research and experiment with emerging multi-agent frameworks (e.g., LangChain, AutoGPT, ReAct) to improve efficiency and capability.

Required Skills & Experience:

Education:

• Bachelor’s or Master’s degree in Computer Science, AI, Machine Learning, or a related technical field.

Experience:

• 5+ years of experience in developing autonomous systems or intelligent agents, particularly in AI or machine learning contexts.

Technical Skills:

• Proficiency with agent architectures (e.g., LangChain, AutoGPT, ReAct) and techniques such as task planning, tool-use, and agent coordination.
• Strong programming skills in Python and experience with AI frameworks for agent-based development.
• Experience with multi-agent systems, including agent communication, task distribution, and collaborative workflows.
• Deep understanding of LLMs and their integration with external APIs, tools, and software systems.

Preferred Skills:

• Familiarity with AI safety and ethics, including preventing unwanted behaviors or biases in autonomous systems.
• Experience in reinforcement learning (RL) and decision-making frameworks.
• Familiarity with cognitive architectures or symbolic reasoning for agent systems.

Work Environment:

Candidates must be willing and able to work on-site at our Phoenix, Arizona facility.

Benefits:

As a valued member of the TSMC family, we place a significant focus on your health and well-being. When