Join our team as an AI Decision Science Analyst focused on Agentic AI and Intelligent Automation. You will play a key role in designing, developing, and deploying advanced enterprise-scale AI solutions. This involves leveraging Large Language Models (LLMs), Agentic AI, and Multi-Agent Systems to build intelligent agents capable of complex reasoning, planning, and autonomous execution of business workflows.

Your work will focus on creating intelligent AI agents using advanced orchestration frameworks and Model Context Protocol (MCP). You'll also develop enterprise AI applications that integrate with critical platforms like ServiceNow, Microsoft Graph, and Azure AI Services, automating business processes and boosting operational efficiency.

We seek individuals to collaborate with solution architects, product owners, and engineers to deliver secure, scalable, and production-ready AI solutions across various industries. This role is central to driving innovation and transforming business operations through cutting-edge AI technologies.

Drive the design, development, and deployment of enterprise AI agents using frameworks like LangGraph and AutoGen. Build sophisticated multi-agent systems for complex tasks, including reasoning, planning, and autonomous execution.

Develop and optimize Large Language Models (LLMs) for enterprise applications, focusing on prompt engineering, function calling, and tool usage. Evaluate AI models rigorously for accuracy, latency, safety, and business KPIs, implementing continuous improvement pipelines.

Design and implement enterprise Retrieval-Augmented Generation (RAG) solutions, optimizing document ingestion, indexing, and retrieval for enhanced AI response accuracy and scalable knowledge management.

Integrate AI agents with key enterprise systems such as ServiceNow, Microsoft Graph API, and Azure Functions, ensuring secure and scalable automation workflows. Develop resilient API integrations with robust error handling and authentication.

Implement AI governance, Responsible AI principles, and robust evaluation frameworks to monitor AI agent performance, cost, and operational health, ensuring compliance and security.

We are looking for an AI Decision Science Analyst with a minimum of 2 years of experience in AI/ML. Demonstrated expertise in Generative AI, Large Language Models (LLMs), Agentic AI systems, and Multi-Agent Systems is essential.

Experience in building and deploying production-grade AI solutions within a consulting or enterprise environment is highly preferred. A Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Machine Learning, or a related technical discipline is required.

Proficiency in Python, SQL, and experience with core AI/LLM technologies such as LangGraph, Azure AI Foundry, Azure OpenAI, and RAG techniques are crucial. Familiarity with enterprise integration patterns and cloud platforms like Azure is beneficial.