What are the responsibilities and job description for the AI Solutions Architect position at Stratedge IT Consulting INC?
Notes:
Only locals to Texas with a Texas ID will be accepted.
No relocation candidates will be considered.
Finalized candidates must show a Texas DL in a video meeting for screenshot capture as part of the compliance process.
State of TX
billing rate 65/hr on c2c 60 on w2
TxDOT has issued a request for an AI Solutions Architect to support Data Governance in building an enterprise agentic AI platform for governed data and AI workflows. The work is centered on architecting production multi-agent systems, reusable AI agents, Snowflake-based data solutions, agent registries, MCP integrations, observability, and human-in-the-loop controls. The ideal candidate has 10 years in software or data engineering, has led a multi-agent platform running in production for at least 12 months, and brings deep hands-on experience with Snowflake, Python, SQL, agent evaluation, LLM observability, security controls, and production-grade AI orchestration.
Responsibilities include (but are not limited to):
- Architect the enterprise agentic AI platform: Design reusable task-specific agents and production multi-agent workflows with planner/worker orchestration, tool calling, state and memory management, error recovery, and an enterprise Agent Registry or Catalog.
- Build governed AI infrastructure: Implement SSO, RBAC, MCP/OpenAI-compatible tool interfaces, sandboxed agent-generated code execution, approval workflows, audit logging, guardrails, rollback procedures, and human-in-the-loop controls.
- Establish production operations and observability: Implement agent evaluation frameworks, regression testing, release quality gates, per-run tracing, token and cost monitoring, failure analysis, and integrations across Snowflake, data engineering, CI/CD, and enterprise systems.
Minimum Candidate Characteristics:
- 10 years in software or data engineering, including at least 3 years building LLM-based systems and 2 years operating agentic AI systems in production serving live business users or workloads; prototypes, pilots, demos, and basic RAG chatbots do not qualify.
- Must have served as lead architect for at least one multi-agent system operating in production for 12 months, with direct ownership of orchestration, tool calling, state/memory management, error recovery, and an Agent Registry or Catalog.
- Strong production experience with Python, SQL, Snowflake/data platforms, CI/CD, LLM evaluation and observability, MCP or OpenAI-compatible interfaces, SSO/SAML/OIDC, RBAC, guardrails, sandboxed code execution, and human approval workflows.
Exceptional Candidate Characteristics:
- Experience with one or more Texas State Agencies.
Responsibilities:
Architect and establish the platform's four foundational pillars:
- Reusable Foundational Agents: Design modular, task-specific AI agents that can be chained together to handle complex data lifecycle tasks.
- Enterprise Applications: Build and deploy user-facing agentic workflows tailored to enterprise needs.
- Balanced Agent Governance: Implement enterprise-grade security including Single Sign-On (SSO), Role-Based Access Control (RBAC), Model Context Protocol (MCP) or OpenAI-compatible standards, and a centralized Agent Catalog.
- Observability & Human-in-the-Loop Controls: Integrate comprehensive monitoring, logging, and guardrails to ensure reliability, transparency, and essential human oversight.
Qualifications & Skills
- Snowflake Mastery: Deep, hands-on experience architecting complex data solutions within the Snowflake ecosystem (including Snowpark, Streamlit, and Cortex AI).
- Agentic AI & LLMs: Proven track record of developing agentic frameworks, multi-agent orchestration, and leveraging open standards (MCP, OpenAI-compatible APIs).
- Data Engineering Infrastructure: Expertise in DBT, SQL, Python, and orchestrating modern ETL/ELT pipelines.
- Enterprise Security: Strong understanding of IAM, SSO, RBAC, and governance frameworks in public sector or highly regulated environments.
- Collaboration: Excellent communication skills to work closely with data engineers, architects, and business stakeholders.
Minimum (Required):
YearsSkills/Experience10Experience in software or data engineering3Experience building LLM-based systems2Experience designing and operating agentic AI systems in production — systems serving live business users or workloads. Prototypes, pilots, internal demos, and RAG chatbots do not meet this bar. Served as the lead architect of at least one multi-agent system that has run in production for 12 months, with direct ownership of supervisory/planner-worker orchestration, tool calling, state and memory management, and error recovery for long-running workflows. Prior experience building Agent Registry or Catalog Production experience with agent-generated code that executes: sandboxed execution, automated validation and testing of generated artifacts, and engineer review-and-approve workflows gating deployment. (Directly relevant — this platform generates executable ingestion code and DBT packages.) Built and operated agent evaluation harnesses in production: offline eval suites, regression testing for prompt and model changes, and measurable quality gates that block release on failure. Operated LLM observability in production: per-run tracing of agent decisions and tool calls, token and cost monitoring, and hands-on triage of agent failures and incidents. Implemented guardrails and human-in-the-loop controls in a governed environment: approval gates, permission-scoped tool access for agents, audit logging, and rollback procedures Has built or deployed MCP servers/clients or OpenAI-compatible tool interfaces in a production system — not just consumed a vendor API. Strong Python and SQL; CI/CD for data platforms; SSO (SAML/OIDC) and RBAC design. Experience with Snowflake (Snowpark, Streamlit, Cortex AI)