This role focuses on designing, developing, configuring, testing, and deploying AI agents and agentic workflows. These solutions will automate business processes, support intelligent decision-making, and integrate seamlessly with enterprise systems.

The core of this position involves hands-on development utilizing Large Language Models (LLMs), memory and state management techniques, external APIs, Retrieval Augmented Generation (RAG), agent orchestration frameworks, and enterprise AI platforms.

Collaboration is key, working closely with Agentic Architects, Integration Developers, and Business Analysts. The goal is to translate business use cases into effective agent solutions capable of reasoning, retrieving information, utilizing tools, managing context, and supporting both human-in-the-loop and fully autonomous workflows.

Develop and implement agent architecture patterns. Engage in agentic AI development and multi-agent workflow design. Master prompt and context engineering for optimal performance. Integrate and evaluate LLMs effectively. Implement agent memory and state management solutions. Design human-in-the-loop (HITL) workflows. Utilize evaluation-driven development methodologies. Implement responsible AI principles and guardrails. Optimize for cost and latency in agent solutions.

A minimum of 3 years of experience is required, specifically with Python. A foundational understanding of Agent Architecture patterns is essential. Experience with agentic AI development and multi-agent workflow design is expected. Proficiency in prompt and context engineering is necessary. Skills in LLM integration and evaluation are required. Experience with agent memory and state management is crucial. Familiarity with human-in-the-loop (HITL) workflow design is beneficial. Understanding of evaluation-driven development principles is important. Knowledge of responsible AI and guardrail implementation is a plus. Ability to optimize for cost and latency is required.