Field AI Agent Designer

Aurigo Software Technologies; Austin (TX); Hybrid; USD 110,000 - 150,000; Full time

Job summary

Aurigo Software Technologies in Austin, TX seeks an Agent Designer to partner with the Domain SME to configure and deploy AI-driven agents in the field, balancing customer needs with what is buildable, scalable, and reliable. You are a co-builder, not a handoff, blending technical depth with domain fluency to guide agent behavior.

You will own training data quality, manage data integrations with agency systems, and lead evaluation of agent performance across multiple deployments, collaborating

Qualifications

• 5+ years in software implementation, solution architecture, or business analysis with customer-facing experience
• Hands-on experience with LLM-based tools, prompt engineering, or agentic workflow platforms
• AI and ML literacy to understand training needs and evaluation of agent outputs
• Ability to operate in ambiguous field environments where requirements emerge from observation

Responsibilities

• Map agency workflows and configure/deploy agents with the Domain SME
• Own training data quality and collaborate with domain SMEs to source labelled examples
• Build and maintain data integrations between Masterworks and agency systems
• Collaborate with agency IT staff, data stewards, and system administrators on access and integration constraints
• Troubleshoot deployment issues in the field and document solutions for reuse

Skills

LLM-based tools

Prompt engineering

Agentic workflows

AI/ML literacy

Field deployment

Tools

Masterworks agent-builder

Job description

Aurigo Software Technologies in Austin, TX seeks an Agent Designer to partner with the Domain SME to configure and deploy AI-driven agents in the field, balancing customer needs with what is buildable, scalable, and reliable. You are a co-builder, not a handoff, blending technical depth with domain fluency to guide agent behavior.

You will own training data quality, manage data integrations with agency systems, and lead evaluation of agent performance across multiple deployments, collaborating