Agentic AI Engineer — Healthcare AI

About the Role

Deloitte is launching a new AI-first initiative, backed by a $1B investment, to transform healthcare decision-making across payers, providers, and life sciences. As an Agentic AI Engineer, you will design, build, and operationalize LLM- and SLM-powered systems to improve clinical reasoning, prior authorization, claims integrity, care navigation, and operational workflows. This is a ground-up rebuild of healthcare decision-making machinery at a national scale, with your work shipping into live clinical and operational settings within months.

Responsibilities

• Agent Architecture & Orchestration:
  • Design and implement agentic systems for multi-step reasoning, planning, tool use, and workflow execution.
  • Build stateful workflows using frameworks like LangGraph and LangChain, including branching, retries, self-correction, and human-in-the-loop checkpoints.
  • Engineer for long-horizon reliability, handling multi-step task completion, error recovery, and planning under uncertainty.
  • Develop reasoning systems for regulated decisions, ensuring policy-grounded outputs, structured reviews, and auditable rationales.
• Retrieval, Grounding & Context Engineering:
  • Develop end-to-end Retrieval-Augmented Generation (RAG) pipelines, including ingestion, chunking, embeddings, retrieval, reranking, and grounding.
  • Engineer memory and context management, ensuring conversational state, persistent memory, and token-efficient context selection.
  • Apply modern context-delivery patterns to ensure 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, and production behavior.
  • Apply guardrails and safety controls to reduce hallucinations and unsafe actions.
  • Evaluate agents at the trajectory and task level, using sandboxed test environments and retrieval/generation-quality metrics.
  • Engineer healthcare-grade safety, including deployment eval gates, human oversight, auditability, and PHI/HIPAA-compliant data handling.
• Integration & Production Craft:
  • Build integrations with internal and external tools, APIs, enterprise systems, and databases.
  • Deliver production-quality code with strong testing, CI/CD, logging, versioning, and documentation practices.
  • Partner with modeling and post-training engineers to improve model behavior for tool use and long-horizon reasoning.
  • Translate complex operational processes into robust system logic and reusable AI patterns.

Required Qualifications

• Bachelor's degree in Computer Science, Engineering, Data Science, Computational Linguistics, or a related field.
• Demonstrated depth in building and shipping production agentic systems, with substantial recent hands-on experience.
• Strong experience with modern orchestration frameworks like LangGraph/LangChain or equivalents.
• Expertise in designing and optimizing end-to-end RAG systems, including indexing, retrieval, reranking, and grounding.
• Deep understanding of memory and context management, including context windows and retrieval-driven context assembly.
• Practical understanding of LLM behavior, limitations, and evaluation methods.
• Experience evaluating and debugging agent behavior at the task and trajectory level.
• Strong Python skills and modern software practices, including testing, CI/CD, and API integration.
• Hands-on experience with frontier model platforms (e.g., Anthropic, Google, OpenAI) and/or open-weight models (e.g., Llama via vLLM).
• Ability to travel 0-50% on average.

Preferred Qualifications

• Experience with multi-agent systems and collaboration patterns.
• Familiarity with vector databases like Pinecone, Weaviate, or Milvus.
• Exposure to model adaptation techniques such as LoRA or QLoRA.
• Understanding of traditional NLP concepts and transformer fundamentals.
• Experience in highly regulated or operationally complex environments; healthcare exposure is a plus.
• Habit of staying current with AI research and emerging engineering patterns.

Compensation

The estimated base salary range is $110,700-$372,900, benchmarked to leading technology companies. Actual pay depends on skills, experience, and level. The role includes a substantial performance-based incentive opportunity, designed to grow with the value created.