Agentic AI Engineer — Healthcare AI
for sections like About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. We must include only sections that have real specific content. The posting includes description (About the role), responsibilities (Work you'll do), required qualifications, preferred qualifications, compensation (Pay). No explicit Benefits or Schedule. So we should have sections: About the role, Responsibilities, Requirements (maybe combine required qualifications?), Qualifications (maybe required?), Skills? The posting includes required qualifications and preferred qualifications; we could treat them as Requirements and Preferred Qualifications? The instruction: use headings for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). We need to decide which to include based on content.
We have:
- About the role: description paragraph at start.
- Responsibilities: "Work you'll do" bullet list.
- Requirements: could be Required Qualifications.
- Qualifications: maybe Preferred Qualifications? Or we could combine required and preferred under Qualifications? But we have both headings available; we could have Requirements (Required Qualifications) and Qualifications (Preferred Qualifications). Or we could have Skills separate? The posting mentions skills like Python, LangGraph, etc. Those are within qualifications. Probably better to have Requirements (Required Qualifications) and Qualifications (Preferred Qualifications). No separate Skills needed.
- Pay: compensation section.
- Benefits: none specific, so omit.
- Schedule: none specific, omit.
We must not repeat job title as heading. No Job ID.
We must preserve all substantive information, not invent or summarize away detail. Must not include boilerplate like EEO etc. The text includes no such boilerplate aside from maybe immigration sponsorship line; that's substantive? It's about limited immigration sponsorship may be available. That's a detail; we should keep it. It's under Required Qualifications? Actually appears after "Ability to travel 0-50%, on average, based on the work you do and the clients and industries/sectors you serve. Limited immigration sponsorship may be available." That's part of qualifications. We'll keep.
We need to use - for any list of duties/requirements/benefits. So for responsibilities list (Work you'll do) we need to turn each bullet into
- . Also for Required Qualifications and Preferred Qualifications we need lists.
We must use
for prose.
We must output only HTML fragment, no /, no markdown fences.
Let's extract content.
About the role: first paragraph up to "This is an early, well-funded build." Actually the description includes multiple sentences. Let's capture:
"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."
That's the about.
Then "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 could be part of About the role or Responsibilities? The "Work you'll do" section follows after that. Actually the text after "Work you'll do" is a heading then bullet list. So we can treat the preceding as About the role.
Thus About the role includes the paragraphs up to "Work you'll do". We'll keep as prose.
Now Responsibilities: list under "Work you'll do". The bullet points:
- Agent architecture & orchestration
- Design and implement agentic systems capable of multi-step reasoning, planning, tool use, and workflow execution against complex, regulated operational processes.
- Build stateful workflows using frameworks such as LangGraph and LangChain - including branching, retries, self-correction, human-in-the-loop checkpoints, and reusable orchestration patterns.
- Engineer for long-horizon reliability - multi-step task completion, recovery from compounding errors, planning under uncertainty, and robust tool use when individual steps fail.
- Build the reasoning behind regulated decisions - policy- and criteria-grounded outputs, structured proposer/critic/judge-style review, and auditable rationales for high-stakes decisions across the industry, from clinical review and prior authorization to claims integrity and care management.
- Retrieval, grounding & context engineering
- Develop end-to-end Retrieval-Augmented Generation (RAG) pipelines: ingestion, chunking, embeddings, vector and hybrid retrieval, reranking, contextual compression, and grounding strategies.
- Engineer memory and context management - conversational state, persistent memory, retrieval-aware context assembly, and token-efficient context selection.
- Apply modern context-delivery patterns (e.g., MCP-style tool/context interfaces) so agents access the right information at the right time.
- Reliability, evaluation & safety
- Implement observability and tracing for prompts, tool calls, retrieval quality, agent traces, failures, drift, latency, and production behavior.
- Apply guardrails, safety controls, and failure-handling to reduce hallucinations and unsafe actions.
- Evaluate agents at the trajectory and task level - multi-step task success, failure-mode and regression analysis, and sandboxed test environments - alongside retrieval- and generation-quality metrics, automated checks, and human review.
- Engineer healthcare-grade safety - deployment eval gates, human-oversight and escalation models, auditability and traceability for regulated decisions, and PHI/HIPAA-aware data handling.
- Integration & production craft
- Build integrations with internal and external tools, APIs, enterprise systems, databases, and model providers so agents operate safely within real business workflows.
- Deliver production-quality code with strong practices in testing, CI/CD, logging, versioning, and documentation; make architecture decisions that balance quality, safety, latency, cost, and model risk.
- Partner with our modeling and post-training engineers to improve model behavior for tool use, grounding, and long-horizon reasoning - through evaluation-driven feedback and, where it helps, fine-tuned or reasoning-optimized models.
- Translate ambiguous, high-complexity operational processes into robust system logic and reusable AI patterns; stay current with advances in agentic systems and translate research into practical engineering decisions.
We need to format as
- for each bullet. The sub-bullets are also list items; we could nest
inside - . That's acceptable.
Now Requirements (Required Qualifications): list:
- Bachelor's degree in Computer Science, Engineering, Data Science, Computational Linguistics, or a related field.
- Demonstrated depth building and shipping production agentic systems - this is your primary craft, not a recent exploration. We weigh shipped systems, research, model releases, and open source over years in a title; expect strong software/ML fundamentals plus substantial, recent hands-on agentic work.
- Strong, hands-on experience building production agent systems with modern orchestration - LangGraph/LangChain or equivalent, including custom orchestration.
- Experience designing and optimizing end-to-end RAG systems: indexing, retrieval, reranking, grounding, and evaluation.
- Strong understanding of memory and context management, including context windows, retrieval-driven context assembly, persistent memory, and high-signal context selection.
- Deep, practical understanding of LLM behavior - strengths, limitations, hallucination risks, reasoning constraints, and latency/cost trade-offs - and the evaluation methods used to measure them.
- Experience evaluating and debugging agent behavior - task-success and trajectory analysis, not just output quality.
- Strong Python engineering skills and modern software practices: testing, CI/CD, version control, and API integration; experience implementing observability, tracing, and debugging for LLM-based systems in production.
- Hands-on experience with at least one frontier model platform (e.g., Anthropic, Google, OpenAI) and/or open-weight/self-hosted models (e.g., Llama via vLLM), including production tool use and agent capabilities.
- Ability to travel 0-50%, on average, based on the work you do and the clients and industries/sectors you serve.
- Limited immigration sponsorship may be available.
We need to keep each as
- .
Now Qualifications (Preferred Qualifications): list:
- Experience with multi-agent systems and agent collaboration patterns.
- Familiarity with vector databases and retrieval infrastructure such as Pinecone, Weaviate, or Milvus.
- Exposure to model adaptation and fine-tuning techniques such as LoRA or QLoRA.
- Understanding of traditional NLP concepts: tokenization, semantic similarity, entity extraction, summarization, and transformer fundamentals.
- Experience operating in highly regulated, high-stakes, or operationally complex environments; healthcare exposure - clinical, payer, or life-sciences workflows, or standards such as FHIR - is a plus, not a requirement.
- Demonstrated habit of staying current with AI research, benchmarks, and emerging engineering patterns.
Now Pay: compensation paragraph:
"Base salary is benchmarked to leading technology companies rather than traditional consulting scales, and the role carries a substantial performance-based incentive opportunity designed to grow with the value you help create - startup-style upside, with the backing of a committed, well-capitalized platform. The estimated base salary range is $110,700-$372,900 (not adjusted for geographic differential); actual base pay depends on your skills, experience, and level, and you may also be eligible for a discretionary annual incentive based on individual and organizational performance."
We'll put that in
under
Pay
.
We must not include Benefits or Schedule.
Now produce HTML fragment.
Structure:
About the role
... paragraphs ...
Responsibilities
- Agent architecture & orchestration
- Design and implement agentic systems capable of multi-step reasoning, planning, tool use, and workflow execution against complex, regulated operational processes.
- Build stateful workflows using frameworks such as LangGraph and LangChain - including branching, retries, self-correction, human-in-the-loop checkpoints, and reusable orchestration patterns.
- Engineer for long-horizon reliability - multi-step task completion, recovery from compounding errors, planning under uncertainty, and robust tool use when individual steps fail.
- Build the reasoning behind regulated decisions - policy- and criteria-grounded outputs, structured proposer/critic/judge-style review, and auditable rationales for high-stakes decisions across the industry, from clinical review and prior authorization to claims integrity and care management.
- Retrieval, grounding & context engineering
- Develop end-to-end Retrieval-Augmented Generation (RAG) pipelines: ingestion, chunking, embeddings,
for prose. We must output only HTML fragment, no /, no markdown fences. Let's extract content. About the role: first paragraph up to "This is an early, well-funded build." Actually the description includes multiple sentences. Let's capture: "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." That's the about. Then "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 could be part of About the role or Responsibilities? The "Work you'll do" section follows after that. Actually the text after "Work you'll do" is a heading then bullet list. So we can treat the preceding as About the role. Thus About the role includes the paragraphs up to "Work you'll do". We'll keep as prose. Now Responsibilities: list under "Work you'll do". The bullet points: - Agent architecture & orchestration - Design and implement agentic systems capable of multi-step reasoning, planning, tool use, and workflow execution against complex, regulated operational processes. - Build stateful workflows using frameworks such as LangGraph and LangChain - including branching, retries, self-correction, human-in-the-loop checkpoints, and reusable orchestration patterns. - Engineer for long-horizon reliability - multi-step task completion, recovery from compounding errors, planning under uncertainty, and robust tool use when individual steps fail. - Build the reasoning behind regulated decisions - policy- and criteria-grounded outputs, structured proposer/critic/judge-style review, and auditable rationales for high-stakes decisions across the industry, from clinical review and prior authorization to claims integrity and care management. - Retrieval, grounding & context engineering - Develop end-to-end Retrieval-Augmented Generation (RAG) pipelines: ingestion, chunking, embeddings, vector and hybrid retrieval, reranking, contextual compression, and grounding strategies. - Engineer memory and context management - conversational state, persistent memory, retrieval-aware context assembly, and token-efficient context selection. - Apply modern context-delivery patterns (e.g., MCP-style tool/context interfaces) so agents access the right information at the right time. - Reliability, evaluation & safety - Implement observability and tracing for prompts, tool calls, retrieval quality, agent traces, failures, drift, latency, and production behavior. - Apply guardrails, safety controls, and failure-handling to reduce hallucinations and unsafe actions. - Evaluate agents at the trajectory and task level - multi-step task success, failure-mode and regression analysis, and sandboxed test environments - alongside retrieval- and generation-quality metrics, automated checks, and human review. - Engineer healthcare-grade safety - deployment eval gates, human-oversight and escalation models, auditability and traceability for regulated decisions, and PHI/HIPAA-aware data handling. - Integration & production craft - Build integrations with internal and external tools, APIs, enterprise systems, databases, and model providers so agents operate safely within real business workflows. - Deliver production-quality code with strong practices in testing, CI/CD, logging, versioning, and documentation; make architecture decisions that balance quality, safety, latency, cost, and model risk. - Partner with our modeling and post-training engineers to improve model behavior for tool use, grounding, and long-horizon reasoning - through evaluation-driven feedback and, where it helps, fine-tuned or reasoning-optimized models. - Translate ambiguous, high-complexity operational processes into robust system logic and reusable AI patterns; stay current with advances in agentic systems and translate research into practical engineering decisions. We need to format as
- for each bullet. The sub-bullets are also list items; we could nest
- inside
- . That's acceptable. Now Requirements (Required Qualifications): list: - Bachelor's degree in Computer Science, Engineering, Data Science, Computational Linguistics, or a related field. - Demonstrated depth building and shipping production agentic systems - this is your primary craft, not a recent exploration. We weigh shipped systems, research, model releases, and open source over years in a title; expect strong software/ML fundamentals plus substantial, recent hands-on agentic work. - Strong, hands-on experience building production agent systems with modern orchestration - LangGraph/LangChain or equivalent, including custom orchestration. - Experience designing and optimizing end-to-end RAG systems: indexing, retrieval, reranking, grounding, and evaluation. - Strong understanding of memory and context management, including context windows, retrieval-driven context assembly, persistent memory, and high-signal context selection. - Deep, practical understanding of LLM behavior - strengths, limitations, hallucination risks, reasoning constraints, and latency/cost trade-offs - and the evaluation methods used to measure them. - Experience evaluating and debugging agent behavior - task-success and trajectory analysis, not just output quality. - Strong Python engineering skills and modern software practices: testing, CI/CD, version control, and API integration; experience implementing observability, tracing, and debugging for LLM-based systems in production. - Hands-on experience with at least one frontier model platform (e.g., Anthropic, Google, OpenAI) and/or open-weight/self-hosted models (e.g., Llama via vLLM), including production tool use and agent capabilities. - Ability to travel 0-50%, on average, based on the work you do and the clients and industries/sectors you serve. - Limited immigration sponsorship may be available. We need to keep each as
- .
Now Qualifications (Preferred Qualifications): list:
- Experience with multi-agent systems and agent collaboration patterns.
- Familiarity with vector databases and retrieval infrastructure such as Pinecone, Weaviate, or Milvus.
- Exposure to model adaptation and fine-tuning techniques such as LoRA or QLoRA.
- Understanding of traditional NLP concepts: tokenization, semantic similarity, entity extraction, summarization, and transformer fundamentals.
- Experience operating in highly regulated, high-stakes, or operationally complex environments; healthcare exposure - clinical, payer, or life-sciences workflows, or standards such as FHIR - is a plus, not a requirement.
- Demonstrated habit of staying current with AI research, benchmarks, and emerging engineering patterns.
Now Pay: compensation paragraph:
"Base salary is benchmarked to leading technology companies rather than traditional consulting scales, and the role carries a substantial performance-based incentive opportunity designed to grow with the value you help create - startup-style upside, with the backing of a committed, well-capitalized platform. The estimated base salary range is $110,700-$372,900 (not adjusted for geographic differential); actual base pay depends on your skills, experience, and level, and you may also be eligible for a discretionary annual incentive based on individual and organizational performance."
We'll put that in
under
Pay
. We must not include Benefits or Schedule. Now produce HTML fragment. Structure:About the role
... paragraphs ...
Responsibilities
- Agent architecture & orchestration
- Design and implement agentic systems capable of multi-step reasoning, planning, tool use, and workflow execution against complex, regulated operational processes.
- Build stateful workflows using frameworks such as LangGraph and LangChain - including branching, retries, self-correction, human-in-the-loop checkpoints, and reusable orchestration patterns.
- Engineer for long-horizon reliability - multi-step task completion, recovery from compounding errors, planning under uncertainty, and robust tool use when individual steps fail.
- Build the reasoning behind regulated decisions - policy- and criteria-grounded outputs, structured proposer/critic/judge-style review, and auditable rationales for high-stakes decisions across the industry, from clinical review and prior authorization to claims integrity and care management.
- Retrieval, grounding & context engineering
- Develop end-to-end Retrieval-Augmented Generation (RAG) pipelines: ingestion, chunking, embeddings,
- Agent architecture & orchestration