AI Prompt Engineer / Agentic AI Engineer
AI Prompt Engineer / Agentic AI Engineer Role Type:Client-facing, hands-on engineering + solutioning (pre-sales through early delivery) Location:Major US hub (e.g., New York, Bay Area, Dallas, Chicago flexible for the right candidate). Hybrid arrangements and travel:This remain hybrid opportunities in New York, the Bay Area, Dallas, or Chicago, with no fully remote option. Travel may be approximately25%, when necessary. Level:Manager/Principal/Senior Principal Business Unit:Enterprise AI Platforms & Agentic Solutions Reporting to:Artificial Intelligence Leader, North America Company Overview: Globaltechnologyconsultinganddigitalsolutionscompanythatenablesenterprisesacrossindustriestoreimaginehowtheyoperate,compete,andgrow.Bycombiningdeepdomainknowledge,advancedengineering,andtransformationexpertise,deliversmeasurablebusinessimpactatscale. EnterpriseAIbusinessunit,purpose builttohelporganizationsmovebeyondpilotsintoscaled,product iongradeAIadoption,functionalconsulting,anAIFoundry,andagenticAIplatformstodeliverintegratedsolutionsthattransformhowworkgetsdone acrosstheenterprise.OperatingacrossBanking,Insurance,Manufacturing,Retail/CPG,Energy&Utilities,Travel&Hospitality,HiTech,andMedia,workscloselywithindustryGTMteamstocreaterepeatableAIsolutions,accelerators,andtransformationprogramsalignedtorealbusinessoutcomes. Role summary The resource will support the design, development, and delivery of AgenticAI solutions by creating, optimizing, and managingAIprompts, agent workflows, and MCP-integrated tools. The role will focus on enabling intelligentAIagents capable of autonomous reasoning, task orchestration, tool utilization, and workflow execution across enterprise applications.
Key Responsibilities
- Design, develop, and optimize prompts for Large Language Models (LLMs) to improve accuracy, reliability, and business outcomes.
- Build and configure AgenticAIsolutions that leverage planning, reasoning, memory, and multi-step task execution capabilities.
- Develop and integrate MCP (Model Context Protocol) tools, enablingAIagents to securely discover and interact with enterprise systems, APIs, and data sources.
- Design agent architectures, tool-calling frameworks, retrieval mechanisms, and context management strategies.
- Collaborate with product managers, architects, andengineering teams to translate business requirements intoAI-driven solutions.
- Implement Retrieval-Augmented Generation (RAG), knowledge grounding, and context orchestration patterns.
- Define evaluation frameworks and prompt testing methodologies to measure agent performance, quality, and reliability.
- EnsureAIsolutions adhere to security, compliance, governance, and responsibleAIstandards.
- Support deployment, monitoring, troubleshooting, and continuous improvement ofAIagents and MCP-enabled workflows.
- Contribute to architecture reviews, technical design documentation, andengineering best practices forAIplatforms.
Required Skill
- Experience with Large Language Models (OpenAI, Azure OpenAI, Anthropic, Gemini, or equivalent).
- Strong understanding of promptengineering,AIagent frameworks, and conversationalAIsystems.
- Experience building AgenticAIapplications using Semantic Kernel, LangChain, LangGraph, AutoGen, CrewAI, or similar frameworks.
- Hands-on experience with MCP servers, tool integration, API orchestration, and enterprise system connectivity.
- Proficiency in Python, TypeScript, or similar programming languages.
- Familiarity with RAG architectures, vector databases, embeddings, and knowledge retrieval systems.
- Understanding of cloud platforms such as AzureAIFoundry, Azure OpenAI, AWS Bedrock, or Google VertexAI.
- Strong problem-solving, analytical, and collaboration skills.
Preferred Qualifications
- Experience building enterprise copilots,AIassistants, or autonomous agent ecosystems.
- Knowledge ofAIgovernance, responsibleAI, and security best practices.
- Experience integratingAIagents with healthcare, health records, or regulated industry systems