Agentic AI Engineer — Healthcare AI
About the role
with. Then: "This is an early, well-funded build. You will own agent systems end to end - from architecture through production - and your work ships into live clinical and operational settings within your first months, not into a lab." That's also about role. Then: "As an Agentic AI Engineer, you will design, build, and operationalize the LLM- and SLM-powered systems behind real healthcare decisioning - the reasoning, orchestration, retrieval, memory, and control layers that let intelligent agents operate reliably across the hardest decisions in the industry: clinical reasoning, prior authorization and claims integrity, care navigation, and the operational workflows that run across payers, providers, and life sciences." That's responsibilities. Then: "This is not a prompt-only role. We are looking for builders who think deeply about system behavior, grounding, and reliability where a wrong action has real consequences for patients and the clinicians who serve them." responsibilities. Then: "You do not need a healthcare background. We pair every engineer with clinical and domain experts and teach you the domain - you bring the agentic engineering depth." responsibilities/qualifications? Could be under Requirements. Then: "We hire on demonstrated depth, not years - the level you join at is determined through our interview process, based on the depth and judgment you demonstrate, not your years in a title." That's about hiring process, maybe under Qualifications. Then: "Work you'll do" heading in original; we need to map to sections. Under "Work you'll do" there are bullet-like paragraphs: - Agent architecture & orchestration: description. - Retrieval, grounding & context engineering: description. - Reliability, evaluation & safety: description. - Integration & production craft: description. These are responsibilities/duties. Could be under Responsibilities as list items. Then: "The team" paragraph: description of team. Could be under About the role or maybe a separate section? Not in headings list. Could be omitted or put under About the role. Then: "Required Qualifications" list: bullet points. Then: "Preferred Qualifications" list. Then: "Compensation" paragraph: base salary range etc. That's Pay section. Also maybe Benefits? Not mentioned. Schedule? Not mentioned. So we should not create Benefits or Schedule sections unless content present. There's no explicit benefits or schedule. So omit those sections. We need to include sections only when posting has real specific content. Thus sections: About the role, Responsibilities, Requirements, Qualifications, Skills?, Pay. Skills: maybe we can extract from Required Qualifications and Preferred Qualifications as skills. But we have separate Requirements and Qualifications sections; we could combine? The instruction: use headings for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). So we can have Requirements and Qualifications separate. Skills maybe not needed if covered elsewhere. But we could still include Skills if we have specific skill list. The posting includes many skill-like items under Required and Preferred. Could create Skills section summarizing those? But we must not invent or summarize away detail; we should preserve all substantive info. If we create Skills section, we need to put the skill details there, but then we would be duplicating content from Requirements/Qualifications. Better to not include Skills if we already have Requirements and Qualifications covering them. The instruction says prefer a few substantive sections over many thin ones. So we can omit Skills. Thus sections: About the role, Responsibilities, Requirements, Qualifications, Pay. Now we need to format. About the role: combine initial paragraphs up to "You will own agent systems end to end..." maybe also include "This is an early, well-funded build." and the description of Deloitte effort. Let's craft a concise but preserve all substantive info: we must not omit details. However we can combine into paragraphs but must keep all info. That's a lot; we need to preserve all substantive information, not invent or summarize away detail. That means we cannot omit any detail; we must keep all facts. But we can rephrase? The instruction: "Preserve ALL substantive information; do NOT invent or summarize away detail." Summarizing away detail is not allowed. So we need to keep the details, but we can still combine sentences? That might be considered summarizing? Probably we need to keep the content verbatim or close. Safer to keep the original sentences as paragraphs. Thus we can output the original text broken into paragraphs under About the role. But we must avoid repeating job title. The posting didn't explicitly give a job title besides "Agentic AI Engineer". We must not repeat that as heading. It's okay to mention in prose. We need to strip boilerplate: cookie/navigation/legal/EEO/equal-opportunity/scam-warning, duplicated lines, application instructions. The text doesn't have those. Now produce HTML. Let's extract sections: About the role: everything before "Work you'll do"? Actually the initial description up to "You will own agent systems end to end - from architecture through production - and your work ships into live clinical and operational settings within your first months, not into a lab." plus maybe the sentence "As an Agentic AI Engineer, you will design, build, and operationalize..." That's more responsibilities. But we can put all pre-work-you-do content into About the role. Let's copy the text from start up to before "Work you'll do". The original: "Three hundred fifty million Americans rely on a healthcare system whose decision-making has become slow, costly, and adversarial - care delayed by prior authorization and paperwork, claims that misfire, clinical decisions made without the right information at the right moment, and patients who struggle to navigate or afford the care they need. Deloitte has a new AI-first effort, backed by $1B in committed investment, building the reasoning models and agentic systems to rebuild how that system decides - across payers, providers, and life sciences, and for the patients they serve - so that care is faster, fairer, and far less wasteful. This is not AI applied at the margins. It is a ground-up rebuild of the decision-making machinery behind American healthcare, at national scale. This is an early, well-funded build. You will own agent systems end to end - from architecture through production - and your work ships into live clinical and operational settings within your first months, not into a lab. As an Agentic AI Engineer, you will design, build, and operationalize the LLM- and SLM-powered systems behind real healthcare decisioning - the reasoning, orchestration, retrieval, memory, and control layers that let intelligent agents operate reliably across the hardest decisions in the industry: clinical reasoning, prior authorization and claims integrity, care navigation, and the operational workflows that run across payers, providers, and life sciences. This is not a prompt-only role. We are looking for builders who think deeply about system behavior, grounding, and reliability where a wrong action has real consequences for patients and the clinicians who serve them. You do not need a healthcare background. We pair every engineer with clinical and domain experts and teach you the domain - you bring the agentic engineering depth. We hire on demonstrated depth, not years - the level you join at is determined through our interview process, based on the depth and judgment you demonstrate, not your years in a title." That seems like About the role + some responsibilities. But we can keep it as About the role. Now Responsibilities: the "Work you'll do" bullet points. We need to format as
- for any list of duties/requirements/benefits. So we can make each bullet as
- .
Thus Responsibilities section:
Responsibilities
- Agent architecture & orchestration ...
- Retrieval, grounding & context engineering ...
- Reliability, evaluation & safety ...
- Integration & production craft ...
Pay
...
Now ensure we didn't miss any substantive info: The "The team" paragraph after "Work you'll do" maybe should be included somewhere. It's substantive. Where to put? Could be under About the role or maybe a separate section like "Team". But not in allowed headings. Could incorporate into About the role as additional paragraph. Let's include it after the About the role paragraph(s). The team paragraph: "The team Deloitte brings together AI researchers, modeling and platform engineers, architects, clinical and domain specialists, and product leaders to build, deploy, and operate verticalized AI systems across software, data, models, and cloud infrastructure - engineered