Agentic AI Solution Architect

Job Title: Agentic AI Solution Architect
Location: Dallas, TX (Remote)
Type: Fulltime
Experience: 10+ Years

Enterprise AI solution architecture on Azure, including Azure AI Foundry / Azure OpenAI, Azure AI Document Intelligence, secure API integration, and production operations.

Hands-on agentic AI and intelligent document processing: orchestration, OCR/layout extraction, cross-document checks, field-level evidence, and human-in-the-loop review.

LLM quality engineering: golden datasets, field-level evaluation, prompt/model versioning, confidence calibration, regression testing, release gates, and monitoring.

Externalized deterministic business rules, governed configuration, audit trail, approval, rollback, and appropriate use of AI ONLY for judgment-based tasks.

Integration design for Power Automate, APIs, Snowflake reference data, enterprise data stores, middleware, and downstream EDM/MDM and SAP item-setup processes.

Security, RBAC, Responsible AI, observability, CI/CD, cost and performance optimization; Python-based implementation experience.

Roles & Responsibilities

Lead the target architecture and establish reusable design patterns for related solution workstreams.

Assess current solution capabilities and recommend evidence-based improvements to document extraction, validation, business rules, and exception handling.

Architect an end-to-end intelligent document-processing workflow covering intake, extraction, validation, enrichment, rule execution, confidence-based exception handling, business approval, and governed downstream integration.

Define traceability for every proposed attribute: source evidence, applied rule, transformation rationale, confidence, reviewer action, and approved value.

Separate deterministic rules from prompts; design business-configurable rules with controlled changes, regression tests, approvals, audit history, and rollback.

Establish golden datasets, evaluation metrics, regression suites, release thresholds, drift monitoring, and feedback loops for prompts, rules, and models.

Design secure integration with existing Azure, Power Platform, reference data, API/middleware, and EDM/MDM/SAP processes; validate interface dependencies before committing to writeback.

Collaborate with Product Managers, enterprise architecture, security, integration, QA, and support teams; produce architecture decisions, diagrams, NFRs, runbooks, and knowledge transfer.