Agentic AI Engineer, Healthcare AI

About the Role

Deloitte is building an AI-first effort to fundamentally rebuild how the healthcare system makes decisions. This initiative is backed by a $1B investment and focuses on creating reasoning models and agentic systems to improve speed, reduce costs, and enhance fairness across payers, providers, life sciences, and patient care. This role is for builders who will own agent systems end-to-end, from architecture to production, with work shipping into live clinical and operational settings.

Key Responsibilities

Agent Architecture & Orchestration

• Design and implement agentic systems for multi-step reasoning, planning, tool use, and workflow execution in 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, including multi-step task completion, recovery from compounding errors, planning under uncertainty, and robust tool use.
• Build reasoning for regulated decisions, including policy- and criteria-grounded outputs, structured review (proposer/critic/judge), and auditable rationales for high-stakes decisions across clinical review, prior authorization, 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, including 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) for agents to 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, including 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, including deployment evaluation 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 to ensure safe operation 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 modeling and post-training engineers to improve model behavior for tool use, grounding, and long-horizon reasoning through evaluation-driven feedback and fine-tuned or reasoning-optimized models.
• Translate complex operational processes into robust system logic and reusable AI patterns.
• Stay current with advances in agentic systems and translate research into practical engineering decisions.

Requirements & Tech Stack

• Python engineering skills
• Modern software practices: testing, CI/CD, version control, API integration
• Experience implementing observability and tracing for LLM-based systems in production
• 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)
• Production tool use and agent capabilities
• LangGraph/LangChain or equivalent for orchestration
• Retrieval-Augmented Generation (RAG) systems: indexing, retrieval, reranking, grounding, evaluation
• Memory and context management: context windows, retrieval-driven context assembly, persistent memory, high-signal context selection
• Deep, practical understanding of LLM behavior, limitations, hallucination risks, reasoning constraints, and latency/cost trade-offs
• Experience evaluating and debugging agent behavior (task-success and trajectory analysis)

Qualifications

• Bachelor's degree in Computer Science, Engineering, Data Science, Computational Linguistics, or a related field.
• Demonstrated depth building and shipping production agentic systems.
• Strong software/ML fundamentals plus substantial, recent hands-on agentic work.
• Strong, hands-on experience building production agent systems with modern orchestration.
• Experience designing and optimizing end-to-end RAG systems.
• Strong understanding of memory and context management.
• Deep, practical understanding of LLM behavior and evaluation methods.
• Experience evaluating and debugging agent behavior.
• Hands-on experience with at least one frontier model platform and/or open-weight/self-hosted models.
• Ability to travel 0-50%.
• Limited immigration sponsorship may be available.

Preferred Qualifications

• 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.
• Demonstrated habit of staying current with AI research, benchmarks, and emerging engineering patterns.