AI Engineer: LLM, RAG & Agentic Workflows

Nexum AI is seeking an AI Engineer to design and build language-model based applications, retrieval systems and intelligent automation that integrate with enterprise workflows. You will move from prototype to reliable production with explicit evaluation, observability and governance.

The role focuses on building LLM applications, RAG pipelines and agent flows that operate with guardrails and human review where needed.

Design LLM applications, RAG pipelines, tool-calling flows and multi-step agents. Evaluate APIs and open-weight models for quality, latency, security and cost. Build services with Python, TypeScript, FastAPI and enterprise APIs. Create reusable evaluation datasets and monitor groundedness and task completion. Implement logging, tracing, versioning and runtime monitoring across platforms. Collaborate with product, data, platform and domain teams to deploy AI into real processes. Expertise in large language model applications and retrieval-augmented systems. Experience designing multi-step agent workflows and context management. Ability to evaluate model quality, latency and security in production. Familiarity with observability, monitoring and governance for AI systems.