AI Solutions Architect (Datagrid)

Procore Technologies

1d • Onsite

About The Position

We’re looking for an AI Agent Solutions Architect for our Datagrid division to lead the design, customization, and deployment of intelligent agent systems in real-world customer environments. This role is ideal for someone who thrives at the intersection of LLM architecture and customer implementation. You’ll design reusable agent frameworks, develop complex prompt strategies, and integrate our agents into customer workflows across enterprise ecosystems. You’ll work cross-functionally with product, engineering, and customer teams to deliver outcomes that scale. This position will report to our Senior Manager, Customer Success Engineering and the location is Bay Area, San Francisco, CA only.

Requirements

• 3+ years in software engineering, ML development, or solutions architecture with 2 years working on LLMs or agentic systems.
• Deep expertise in prompt engineering, agent orchestration, tool use, and stateful reasoning systems
• Hands-on experience with frameworks like LangChain, AutoGen, Semantic Kernel, or similar.
• Strong programming skills in Python and familiarity with APIs, webhooks, and AI infrastructure.
• Experience deploying AI-driven systems in enterprise or production environments.
• Familiarity with vector databases, embeddings, and RAG architecture.
• Strong client communication skills and a passion for delivering AI that solves real problems

Nice To Haves

• Knowledge of symbolic reasoning, knowledge graphs, or multi-modal agents.

Responsibilities

• Design modular, scalable AI agents that reason, take action, and communicate with users across channels.
• Meet with and partner closely with customers to understand their use cases and tailor agent workflows to their systems, tools, and data.
• Build and optimize multi-step agent chains using prompt engineering, tool integration, and memory/state handling.
• Develop proof-of-concept deployments and iterate toward production-ready solutions with enterprise clients.
• Integrate external APIs, databases, internal systems, and retrieval-augmented generation (RAG) pipelines into agent frameworks.
• Work alongside ML engineers to define performance metrics and improve agent reliability and explainability.
• Build internal tooling for prompt versioning, A/B testing, and agent performance feedback loops.
• Contribute to reusable design patterns, internal documentation, and knowledge sharing for field-facing solutions.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: No Education Listed
• Number of Employees: 11-50 employees