Skip to main content

About the role

Role: AI / Agentic AI Solution Architect
Location: Dallas, TX / Remote (Onsite)
Fulltime - Permanent
Job Description
Must Have Technical/Functional Skills: 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.

Before you apply

Applying takes about a minute. These four things decide how fast it moves after that.

Your profile is current

It's what we read first. Occupations, seniority and locations matter more than a long history.

Two examples you can talk through

Not a portfolio — just two pieces of work where you can explain the decisions and what you'd change.

A number in mind

What you're on now and what would make you move. We negotiate better when we know both.

Your notice period

Employers plan around it, and it's the question that stalls offers most often.

Once you apply, someone reads it and calls you before anything reaches the employer — usually within two working days.

More like this