AI Agent Builder

University of Washington•Seattle, WA

1d•$87,624 - $142,392•Hybrid

About The Position

UW Information Technology has an outstanding opportunity for an AI Agent Builder to join their team. Reporting to a Technology Manager in Infrastructure Service and AI Platforms, the AI Agent Builder will support the artificial intelligence (AI) initiatives at the university and its three campuses. This role is a pivotal role in shaping and implementing our AI strategy to transform UW into an AI-powered University. The AI Agent Builder is a core technical role within the AI Platforms team, focused on the design, development, deployment, and ongoing enhancement of AI-powered agents and intelligent automation solutions that serve the university. The AI Agent Builder Engineer role will work within Service Management and AI Platform team under the UW's IT infrastructure Umbrella that provides critical technology support to all three campuses, UW Medicine, and research operations around the world.

Requirements

Bachelor's degree in Computer Science, Data Science, Software Engineering, or a related field or experience.
3 + years of professional software development experience demonstrating strong computer science fundamentals and API integration expertise, professional experience in software development.
Demonstrated experience in AI/ML or LLM-based applications.
Demonstrated portfolio of deployed AI agent solutions or automation tools (GitHub repositories, case studies, or equivalent evidence of hands-on work).
Demonstrated experience building AI agents, chatbots, or conversational AI systems using modern LLM frameworks.
Hands-on experience with LLM APIs (e.g., OpenAI, Anthropic, Google, or open-source models) and prompt engineering.
Strong understanding of retrieval-augmented generation (RAG), embeddings, vector search, and contextual grounding strategies.
Familiarity with vector databases (e.g., Pinecone, Weaviate, ChromaDB, pgvector) and embedding-based retrieval.
Experience with REST APIs, cloud platforms (AWS, Azure, or GCP), and containerization (Docker).
Strong problem-solving skills and ability to work both independently and collaboratively in a cross-functional teams.

Nice To Haves

Experience working in higher education, research institutions, or the public sector.
Demonstrated experience designing, building, and iterating on AI agents
Experience with enterprise AI orchestration platforms such as nebulaONE or comparable environments.
Experience with agent-to-agent (A2A) coordination models and advanced tool-use frameworks.
Experience with fine-tuning, evaluation, or alignment of language models.
Knowledge of data privacy regulations (FERPA, HIPAA) and responsible AI principles.
Experience building no-code/low-code tools or platforms for non-technical users.
Contributions to open-source AI/ML projects.
Experience with REST API and MCP integrations is highly desirable; familiarity with A2A integrations is a plus but not required.

Responsibilities

Demonstrated experience designing, building, and iterating on AI agents to improve performance, functionality, and user outcomes.
Architect and implement advanced RAG pipelines, including embedding strategies, vector search optimization, contextual window management, and hybrid retrieval techniques.
Identify and automate repetitive administrative processes across departments using AI-powered workflows.
Integrate AI agents with university enterprise systems (e.g., SIS, LMS, HRIS, ERP, ticketing systems) via APIs and connectors.
Build AI tools that assist researchers with literature review, data analysis, grant writing support, and knowledge synthesis.
Support advanced use cases involving long-context reasoning, structured data augmentation, and research corpus grounding.
Develop bespoke AI-powered tools tailored to departmental needs (e.g., document drafting assistants, scheduling agents, data query tools).
Implement agent orchestration frameworks such as CrewAI or equivalent enterprise-grade platforms; experience with nebulaONE or similar orchestration environments is highly desirable.
Monitor agent performance, usage analytics, and user feedback to continuously improve deployed solutions.
Implement guardrails, safety mechanisms, and evaluation frameworks to ensure responsible AI behavior.