About Echelon: Echelon is building an AI platform for Business Operations to automate the knowledge work of BizOps. We are an early-stage company delivering production systems and owning outcomes. This role focuses on designing and shipping production agents and multi-agent coordination that operate on ambiguous, high-stakes operational problems rather than controlled demos. You will design agent loops, tool-use patterns, evaluation systems, and orchestration for agent swarms, with emphasis on reliability and safety. What you'll own: Design and ship production agents that plan, retrieve context, call tools, generate artifacts, and complete multi-step work. Build orchestration patterns for specialized agents and agent swarms, including task decomposition, delegation, shared state, recovery, and human approval. Create evaluation suites for task success, factuality, tool selection, safety, latency, and cost. Improve context engineering across prompts, retrieval, memory, structured state, documents, and the Echelon ontology. Build guardrails for permissions, tenant isolation, sensitive data, unsafe actions, and unreliable model output. Compare models and prompting strategies with production traces and measured outcomes rather than intuition. Partner with Product Engineering and domain experts to turn real BizOps workflows into dependable agent capabilities. Own failures in production and improve the architecture until the same class of failure cannot recur. What you bring: 4+ years building production software, including substantial hands-on work with LLM or ML-powered products

About Echelon: Echelon is building an AI platform for Business Operations to automate the knowledge work of BizOps. We are an early-stage company delivering production systems and owning outcomes. This role focuses on designing and shipping production agents and multi-agent coordination that operate on ambiguous, high-stakes operational problems rather than controlled demos. You will design agent loops, tool-use patterns, evaluation systems, and orchestration for agent swarms, with emphasis on reliability and safety. What you'll own: Design and ship production agents that plan, retrieve context, call tools, generate artifacts, and complete multi-step work. Build orchestration patterns for specialized agents and agent swarms, including task decomposition, delegation, shared state, recovery, and human approval. Create evaluation suites for task success, factuality, tool selection, safety, latency, and cost. Improve context engineering across prompts, retrieval, memory, structured state, documents, and the Echelon ontology. Build guardrails for permissions, tenant isolation, sensitive data, unsafe actions, and unreliable model output. Compare models and prompting strategies with production traces and measured outcomes rather than intuition. Partner with Product Engineering and domain experts to turn real BizOps workflows into dependable agent capabilities. Own failures in production and improve the architecture until the same class of failure cannot recur. What you bring: 4+ years building production software, including substantial hands-on work with LLM or ML-powered products