AI Platform Engineer & Workflow Architect

Synergis

Dallas (TX)

On-site

USD 110,000 - 113,000

Full time

20 hours ago

Be an early applicant

Get more replies from employers

Send a job-specific resume in minutes.

Benefits offered by this job

medical

dental

vision

disability

life insurance

401k

commuter benefits

Job summary

Synergis seeks an AI Platform Engineer/AI Workflow Builder in Dallas to architect and maintain AI-augmented workflows. You will transform institutional knowledge into structured AI-ready data and build durable schemas and rules used across multiple AI tools.

You will connect AI agents to live knowledge sources, automate handoffs to Jira, and instrument telemetry for performance evaluation. Responsibilities include maintaining CI/CD pipelines for AI-enabled workflows, ensuring traceability from

Qualifications

Hands-on experience building AI agents and multi-step workflows.
Experience restructuring complex, fragmented information into usable AI-ready systems.
Experience with MCP or related patterns for connecting LLMs to live knowledge sources, files, repositories, tools, and data.
Proficiency in Python, TypeScript, Node.js, APIs, systems integration, automation, and data pipelines.

Responsibilities

Build and maintain knowledge sources AI agents use to understand design standards, user research, accessibility requirements, front-end components, brand guidance, and writing standards.
Transform existing documents, design files, and undocumented institutional knowledge into structured information that AI agents can reliably search and use.
Establish separation between AI tools and information they consume so tools remain portable and reusable.
Create durable schemas, taxonomies, metadata structures, and reference identifiers for traceability across systems.
Build a centralized set of design and accessibility rules for multiple AI tools and automated quality checks.
Maintain traceability as work moves from research findings through design and into working software.
Build instrumentation and telemetry into AI workflows to measure performance and outcomes.
Tune automated checks to reduce false positives and document exceptions.
Connect AI agents to live knowledge sources, design files, research data, and code repositories using MCP and related patterns.
Automate workflow steps between design, engineering, and platforms such as Jira.
Build and maintain CI/CD pipelines supporting AI-enabled workflows and internal tools.
Create written playbooks so new ways of working remain durable across tools and platforms.
Identify additional manual design and development workflows that can be reliably automated.