Deloitte offers an on-site opportunity in Miami, FL for an Agentic AI Engineer focused on Healthcare AI. This role centers on designing, building, and operationalizing LLM- and SLM-powered decisioning systems across payers, providers, and life sciences. You will own agent systems end to end and deploy them into live clinical and operational settings within a matter of months. The position features a competitive base salary range of USD 110,700 to 372,900 per year, plus a substantial performance-based incentive and startup-style upside, backed by a well-capitalized platform. You will collaborate with AI researchers, modeling and platform engineers, clinical and domain experts, and product leaders to tackle genuinely hard healthcare reasoning problems in real-world workflows.
Responsibilities
- Design and deploy agentic systems that perform multi-step reasoning, planning, tool use, and workflow execution within complex, regulated healthcare processes.
- Construct stateful workflows with LangGraph and LangChain, including branching, retries, self-correction, human-in-the-loop checkpoints, and reusable orchestration patterns.
- Focus on long-horizon reliability: ensure multi-step task completion, recover from cascading errors, plan under uncertainty, and maintain robust tool use when steps fail.
- Develop the reasoning behind regulated decisions with policy-grounded outputs, structured proposer/critic/judge-style reviews, and auditable rationales for high-stakes decisions across clinical review, prior authorization, claims integrity, and care management.
- Build end-to-end Retrieval-Augmented Generation 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 to ensure agents access the right information at the right time using tool and context interfaces.
- Implement observability and tracing for prompts, tool calls, retrieval quality, agent traces, failures, drift, latency, and production behavior.
- Incorporate guardrails, safety controls, and failure-handling to reduce hallucinations and unsafe actions.
- Evaluate agents at trajectory and task levels with multi-step task success metrics, failure-mode analysis, and sandboxed testing, alongside retrieval and generation quality metrics and automated checks with human review.
- Institute healthcare-grade safety through deployment eval gates, human oversight and escalation models, auditable traceability for regulated decisions, and PHI/HIPAA-aware data handling.
- Build integrations with internal and external tools, APIs, enterprise systems, databases, and model providers to keep agents aligned with real business workflows.
- Deliver production-quality code with strong testing, CI/CD, logging, versioning, and documentation; make architecture decisions balancing quality, safety, latency, cost, and model risk.
- Collaborate with modeling and post-training engineers to improve model behavior for tool use, grounding, and long-horizon reasoning through evaluation-driven feedback and, where helpful, 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.
Requirements
- Bachelor's degree in Computer Science, Engineering, Data Science, Computational Linguistics, or a related field.
- Proven track record shipping production agentic systems; this is the core craft, with emphasis on long-term ownership, not recent exploration. Strong software/ML fundamentals plus substantial, recent hands-on agentic work.
- Hands-on experience building production agent systems with modern orchestration frameworks such as LangGraph or LangChain, including custom orchestration.
- Experience designing and optimizing end-to-end RAG systems: indexing, retrieval, reranking, grounding, and evaluation.
- Strong memory and context management expertise, including context windows, retrieval-driven context assembly, persistent memory, and high-signal context selection.
- Deep practical understanding of LLM behavior, including strengths, limitations, hallucination risks, reasoning constraints, and latency/cost trade-offs, plus the evaluation methods used to measure them.
- Experience evaluating and debugging agent behavior with a focus on 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 production LLM-based systems.
- Hands-on experience with at least one frontier model platform (Anthropic, Google, OpenAI) and/or open-weight/self-hosted models (Llama via vLLM), including production tool use and agent capabilities.
- Ability to travel up to 50 percent, depending on work and client needs.
- Limited immigration sponsorship may be available.
Technologies
- LangGraph
- LangChain
- Pinecone
- Weaviate
- Milvus
- Llama via vLLM
- Anthropic
- Google
- OpenAI
- Python
The Team
Deloitte brings together AI researchers, modeling and platform engineers, architects, clinical and domain specialists, and product leaders to build, deploy, and operate vertical AI systems across software, data, models, and cloud infrastructure. The healthcare focus spans payers, providers, and life sciences, confronting genuinely hard reasoning problems, nuanced operational workflows, and a high bar for quality.
Compensation
Base salary is benchmarked to leading technology companies rather than traditional consulting scales, with a substantial performance-based incentive opportunity and startup-style upside, supported by a committed, well-capitalized platform. The estimated base salary range is 110,700 to 372,900 USD per year, not adjusted for geographic differential; actual pay depends on skills and experience.
