About ELLKAY :

ELLKAY is a trusted data management partner in five healthcare segments. We serve laboratories, ambulatory practices, hospitals, health systems, healthcare IT vendors, and health plans with cutting-edge technologies that drive growth and interoperability.

Job Description :

Build production LLM applications and agent workflows for implementation assistance, connector capability discovery, migration operations, and archive access. The engineer will implement retrieval, tool integration, workflow state, citations, approval checkpoints, and automated evaluation.

Essential Duties :

- Build RAG and tool-calling workflows for implementation assistance, connector capability discovery, error explanation, and guided migration operations.

- Create context assembly from approved documentation, run status, mapping metadata, and evidence.

- Implement MCP clients/tool integrations and thin adapters over platform contracts.

- Handle async request IDs, retries, timeouts, and duplicate action prevention.

- Implement permission-aware retrieval, approval checkpoints, prompt-injection defenses, and bounded tool use.

- Capture agent traces, user feedback, and add regression tests for prompts, tool selection, and retrieval quality.

- Improve retrieval and context assembly using measured failures.

- Partner with Data Platform and product engineers, clinical/data SMEs, DME/QA, and security teams.

Qualifications :

- 5+ years in software/AI engineering, including production LLM applications and backend services.

- Strong Python, REST APIs, asynchronous programming, data handling, software testing, and production debugging.

- Hands-on RAG, hybrid/vector search, embeddings, reranking, structured outputs, and tool calling.

- Experience implementing agent state, timeouts, bounded retries, approval checkpoints, and fallback.

- Ability to evaluate retrieval relevance, groundedness, tool selection, task completion, latency, and unit cost.

- Experience deploying services to a cloud environment and implementing authorization-aware retrieval and PHI-safe telemetry.

Preferred Qualifications :

- MCP, LangGraph or equivalent agent orchestration, FastAPI, AWS, Docker/Kubernetes, HL7/FHIR familiarity, and enterprise authorization patterns.