We are seeking an Agentic AI Engineer (2+ years, with a robust software/ML engineering foundation) to build and test agentic AI workflows in equal measure. This is a hands-on engineering role split roughly 50/50 between developing multi-step agent pipelines - orchestration, tool/function calling, state and memory, error recovery - and rigorously debugging and evaluating them. The person will instrument agents for observability and root-cause analysis, design evaluation suites that separate linguistic robustness from intent fulfilment, validate RAG and vector retrieval, and embed continuous LLM evaluation into CI/CD (LLMOps) pipelines. The role also involves engaging directly with client stakeholders and collaborating across cross-functional teams to align reliability and quality goals with business objectives and deliver scalable, high-quality Generative AI solutions.