Senior AI Orchestration Engineer & Technical Program Lead (Healthcare)

3+ years in LLM/prompt engineering, structured generation, evaluation workflows. 4–8 years hands‑on development with technical leadership/TPM experience. Expertise in Azure Orchestration: Azure Functions Durable, Azure Container Apps, Azure Queues/Event Grid, KEDA. Expertise in Azure Data: Azure Blob/ADLS Gen2, Azure AI Search (vector), CosmosDB/SQL, Redis. Expertise in Azure Observability: App Insights, Azure Monitor, OpenTelemetry. Expertise in CI/CD: GitHub Actions; environments; PR‑based governance; prompt/version management. Proficient in TypeScript/React for front‑ends. Proficient in Python/Node.js for services/workers/tooling. Experience with REST/gRPC; async jobs and streaming outputs; webhook/callback patterns. Experience with Multi‑model orchestration (GPT‑4.1/5 + SLMs). Experience with RAG pipelines; embeddings; retrieval strategies; evaluation and guardrails. Experience with Tool‑calling/MCP; remote and custom‑hosted tool integration. Familiarity with healthcare data models (FHIR) and regulated environments. Familiarity with Security/compliance: HIPAA, SOC 2. Facilitate technical design sessions to consensus. Run sprints/meetings that produce decisions.

Design and deploy LLM solutions with deterministic, multi-step prompt chaining. Implement structured generation pipelines and evaluation harnesses. Operationalize RAG pipelines from Azure Blob/ADLS Gen2. Integrate and debug complex multi-model setups. Standardize tool-calling for EHR/EMR, scheduling, and internal APIs. Establish flows-as-code, prompt versioning, environments, and CI/CD. Translate AI/product vision into technical roadmaps. Operate a GA-ready Azure stack for orchestration, retries, and auto-scaling. Implement observability with Azure Monitor/App Insights/OpenTelemetry. Ensure reliability, performance, concurrency, cost optimization, and resilience. Facilitate technical design sessions and run decisive meetings. Document processes, architectures, and technical decisions clearly. Promote psychological safety and facilitate AI-focused problem-solving.