Staff Applied AI Engineer - Agentic Healthcare AI

Arcadia; Northern (KY); Hybrid; USD 175,000 - 200,000; Full time

Benefits offered by this job

Remote-friendly culture

Employee development programs

Job summary

Arcadia is seeking a staff-level software engineer focusing on agentic AI, responsible for shaping agent behavior, retrieval, memory, and escalation in production healthcare workflows. You will partner with Product and Engineering to deliver scalable, trustworthy AI that supports clinicians and care teams.

Responsibilities include designing data-grounded prompts, building evaluations, and ensuring safety and cost-aware performance while maintaining documentation and model cards for internal

Qualifications

• 8+ years of production software engineering experience, with 3+ years owning ML/LLM or agentic systems in production, preferably in regulated industries such as healthcare or finance.

Responsibilities

• Design and iterate on agent behavior across real, live workflows, including long-horizon, multi-turn tasks.
• Design retrieval and context architecture to ensure data reaches models in the right structure for grounded agent behavior.
• Design memory and state handling across multi-turn and multi-agent flows; determine what to carry forward or drop.
• Create context and prompt templates using few-shot examples and structured formatting for consistent agent behavior.
• Build and run evaluations against production conditions to measure performance, regressions, and edge cases.
• Author evaluation rubrics and thresholds to weight failures by severity and cost; monitor production behavior.

Skills

Production software

ML/LLM

RAG architecture

SageMaker / Bedrock

Healthcare domain

Job description

Arcadia is seeking a staff-level software engineer focusing on agentic AI, responsible for shaping agent behavior, retrieval, memory, and escalation in production healthcare workflows. You will partner with Product and Engineering to deliver scalable, trustworthy AI that supports clinicians and care teams.

Responsibilities include designing data-grounded prompts, building evaluations, and ensuring safety and cost-aware performance while maintaining documentation and model cards for internal