<h1>Role - Senior AI Engineer</h1>
<h1>About the Role</h1>
<p>GHX is building an LLM-powered document understanding platform — classification, structured data extraction, and intelligent orchestration at scale. This is a broad AI engineering role where you will own the full lifecycle from problem framing through to production quality.</p>
<p>You will start where the highest leverage is: designing prompts that behave like specifications and building the evaluation infrastructure that tells us whether the system actually works. Over time, the scope expands into agent orchestration, system architecture, and the migration of our existing rule-based pipeline to LLM-based equivalents.</p>
<p>Solid software engineering experience is a pre-requisite. You will design and build production services, own architectural decisions, and write code that others maintain. AI fluency amplifies good engineering – it does not replace it.</p>
<p> </p>
<table width="624">
<tbody>
<tr>
<td width="16">
<p> </p>
</td>
<td width="608">
<p><em>This role requires 8+ years of software engineering experience as a foundation. The expectation is that you bring the same rigor to system design and code quality as you do to the prompt design and model evaluation. You know what should happen before evaluating what did happen — and the discipline to close that gap rigorously.</em></p>
</td>
</tr>
</tbody>
</table>
<p> </p>
<h1>How the Role Evolves</h1>
<table width="624">
<tbody>
<tr>
<td width="96">
<p><strong>Now</strong></p>
</td>
<td width="528">
<p><strong>Prompt engineering & LLM evaluation</strong></p>
<p>Design classification and extraction prompts, build ground truth datasets, create evaluation pipelines, and establish the quality baseline the team will build on.</p>
</td>
</tr>
</tbody>
</table>
<p> </p>
<table width="624">
<tbody>
<tr>
<td width="96">
<p><strong>6–12 mo</strong></p>
</td>
<td width="528">
<p><strong>Agent orchestration & pipeline design</strong></p>
<p>Extend into multi-agent document processing pipelines, MCP-based tool integration, and orchestration of parallel AI workstreams.</p>
</td>
</tr>
</tbody>
</table>
<p> </p>
<table width="624">
<tbody>
<tr>
<td width="96">
<p><strong>12 mo+</strong></p>
</td>
<td width="528">
<p><strong>Platform architecture & migration ownership</strong></p>
<p>Own the architecture of the document intelligence layer, lead the migration from rule-based systems, and define engineering standards for the team.</p>
</td>
</tr>
</tbody>
</table>
<p> </p>
<h1>Core Responsibilities</h1>
<h2>Prompt Engineering</h2>
<ul>
<li>Design classification and extraction prompts for diverse document types</li>
<li>Write prompts that function as formal specifications — unambiguous and edge-case-aware</li>
<li>Build and iterate few-shot, chain-of-thought, and structured output templates</li>
<li>Own the prompt library, versioning, and rollback strategy</li>
</ul>
<h2>LLM Output Evaluation</h2>
<ul>
<li>Define and curate ground truth datasets for classification and extraction tasks</li>
<li>Build automated evaluation pipelines tracking precision, recall, and field-level accuracy</li>
<li>Validate outputs against intent — catch what is technically correct but conceptually wrong</li>
</ul>
<h2>AI Agent Orchestration</h2>
<ul>
<li>Design multi-agent pipelines for document processing workflows</li>
<li>Integrate MCP servers and tool-use patterns for external service access</li>
</ul>
<h2>Software Engineering</h2>
<ul>
<li>Build production-grade APIs and services around LLM capabilities</li>
<li>Apply Clean Architecture or equivalent — design for testability and maintainability</li>
<li>Write well-structured Python; own technical debt decisions consciously</li>
<li>Contribute to CI/CD, observability, and deployment pipelines</li>
</ul>
<h2>Stakeholder Interface</h2>
<ul>
<li>Serve as technical contact between business teams and the AI engineering layer</li>
<li>Communicate system constraints in product language; translate product needs into system boundaries</li>
<li>Surface quality metrics and model behaviour to non-technical stakeholders</li>
</ul>
<h1>Skills & Experience</h1>
<h2>Required</h2>
<ul>
<li>Prompt engineering (advanced) & LLM evaluation frameworks</li>
<li>Ground truth dataset design</li>
<li>LLM APIs — OpenAI, Anthropic, Azure AI</li>
<li>8+ years overall software engineering experience preferably in Python & AWS</li>
<li>AI agent orchestration</li>
<li>Clean Architecture / DDD</li>
<li>REST API design</li>
<li>Git, CI/CD, containerisation</li>
</ul>
<h2>Nice to Have</h2>
<ul>
<li>Document understanding / OCR tooling like Textract</li>
<li>Experience working with AWS services (EC2, SQS, S3, Lambda functions, ECS)</li>
<li>LangChain / LlamaIndex</li>
<li>NLP / text classification</li>
</ul>
<h1>What Good Looks Like</h1>
<ul>
<li><strong>Prompt as specification. </strong>Treats prompts like specifications — precise, contract-like, with edge cases considered upfront rather than patched later.</li>
<li><strong>Verification instinct. </strong>Reads AI output critically. Catches the subtly wrong answer before it becomes an expensive data quality incident downstream.</li>
<li><strong>Evaluation-first mindset. </strong>Doesn't trust a prompt in production without a test suite. Builds measurement infrastructure as part of the feature, not after.</li>
<li><strong>Architectural thinking. </strong>Understands how systems should be structured before implementation begins. Knows the difference between technically correct and conceptually right.</li>
<li><strong>Pattern fluency. </strong>Knows Clean Architecture, DDD, or equivalent — not the syntax, the reasoning behind the design choices.</li>
<li><strong>Communication range. </strong>Can speak to a non-technical ops manager and a distributed system at the same level of precision.</li>
</ul>
<p> </p><div class="content-conclusion"><p><strong data-stringify-type="bold">GHX: It's the way you do business in healthcare</strong><br>Global Healthcare Exchange (GHX) enables better patient care and billions in savings for the healthcare community by maximizing automation, efficiency and accuracy of business processes.</p>
<p>GHX is a healthcare business and data automation company, empowering healthcare organizations to enable better patient care and maximize industry savings using our world class cloud-based supply chain technology exchange platform, solutions, analytics and services. We bring together healthcare providers and manufacturers and distributors in North America and Europe - who rely on smart, secure healthcare-focused technology and comprehensive data to automate their business processes and make more informed decisions.</p>
<p>It is our passion and vision for a more operationally efficient healthcare supply chain, helping organizations reduce - not shift - the cost of doing business, paving the way to delivering patient care more effectively. Together we take more than a billion dollars out of the cost of delivering healthcare every year. GHX is privately owned, operates in the United States, Canada and Europe, and employs more than 1000 people worldwide. Our corporate headquarters is in Colorado, with additional offices in Europe.</p>
<p><strong data-stringify-type="bold"><em data-stringify-type="italic">Disclaimer</em></strong><br><em data-stringify-type="italic">Global Healthcare Exchange, LLC and its North American subsidiaries (collectively, “GHX”) provides equal employment opportunities (EEO) to all employees and applicants for employment without regard to race, color, national origin, sex, sexual orientation, gender identity, religion, age, genetic information, disability, veteran status or any other status protected by applicable law. All qualified applicants will receive consideration for employment without regard to any status protected by applicable law. This EEO policy applies to all terms, conditions, and privileges of employment, including hiring, training and development, promotion, transfer, compensation, benefits, educational assistance, termination, layoffs, social and recreational programs, and retirement.</em><em data-stringify-type="italic">GHX believes that employees should be provided with a working environment which enables each employee to be productive and to work to the best of his or her ability. We do not condone or tolerate an atmosphere of intimidation or harassment based on race, color, national origin, sex, sexual orientation, gender identity, religion, age, genetic information, disability, veteran status or any other status protected by applicable law. GHX expects and requires the cooperation of all employees in maintaining a discrimination and harassment-free atmosphere. Improper interference with the ability of GHX’s employees to perform their expected job duties is absolutely not tolerated.</em></p>
<p><em data-stringify-type="italic">Read our <a href="https://www.ghx.com/privacy-notice-for-personnel-and-applicants/" target="_blank">GHX Privacy Policy</a></em></p></div>
