Orchestration Developer

World Wide Technology Healthcare Solutions•Jenks, OK

1d•Onsite

About The Position

We are seeking an orchestration developer to design, build, and operate distributed execution platforms that support agentic, AI-driven workflows and system-to-system coordination at scale. This role focuses on building reliable, asynchronous systems that enable autonomous decision-making, multi-step execution, and collaboration between intelligent agents. You will work at the platform layer, enabling AI-powered components to reason, communicate, and act safely within well-defined system boundaries.

Requirements

3–6 years of backend or platform development experience
Strong experience with distributed or asynchronous systems
Experience designing event‑driven or message‑oriented architectures
Proficiency designing APIs and service‑to‑service communication
Strong system‑level debugging and problem‑solving skills
Familiarity with MCP, A2A protocols, Node.js, Python

Nice To Haves

Experience working with AI‑powered or agentic systems
Familiarity with LLM integration, tool invocation, or RAG‑based architectures
Experience building resilient systems that tolerate partial failure
Exposure to observability, tracing, or evaluation in complex platforms
Experience with OpenShift / Kubernetes or other containerization platform technologies

Responsibilities

Design and implement distributed workflow and execution components
Build asynchronous, event-driven communication between services and agents
Implement coordination, delegation, and handoff patterns across agent-based systems
Develop APIs and internal services supporting execution pipelines
Manage state, memory, and context across multi-step workflows
Integrate large language models (LLMs) as controlled system components
Implement guardrails, structured outputs, retries, and fallback behaviors
Support agent-to-agent communication and tool invocation patterns
Ensure AI and agent behavior is observable, traceable, and auditable
Design failure handling, idempotency, and retry strategies for autonomous execution
Improve observability through logging, metrics, and tracing
Debug complex, multi-step execution issues in distributed systems
Contribute to platform scalability, performance, and operational maturity