AI Prompt Engineer / Agentic AI Engineer
Location: Remote
Employment Type: Contract, W2
Experience: 6+ Years
Rate: $50/hour on W2
Job Description
We are seeking an experienced AI Prompt Engineer / Agentic AI Engineer to design, develop, and deliver enterprise-grade Agentic AI solutions.
The ideal candidate will have hands-on experience building LLM-powered applications, autonomous AI agents, RAG solutions, agent workflows, and tool-integrated AI systems. This role will focus on prompt engineering, agent orchestration, MCP-enabled tool integration, contextual reasoning, retrieval, and reliable multi-step workflow execution.
The engineer will work closely with product managers, architects, and engineering teams to translate business requirements into scalable AI solutions.
Key Responsibilities
- Design, develop, test, and optimize prompts for Large Language Models to improve accuracy, reliability, and business outcomes.
- Build Agentic AI applications capable of planning, reasoning, memory management, tool utilization, and multi-step task execution.
- Develop and integrate MCP (Model Context Protocol) servers and tools for secure interaction with enterprise applications, APIs, and data sources.
- Design agent architectures, tool-calling frameworks, retrieval mechanisms, and context-management strategies.
- Build and optimize Retrieval-Augmented Generation (RAG) solutions using vector databases, embeddings, semantic search, and knowledge grounding.
- Develop autonomous and multi-agent workflows using frameworks such as LangChain, LangGraph, Semantic Kernel, AutoGen, CrewAI, or similar technologies.
- Integrate AI agents with enterprise APIs, databases, applications, and external tools.
- Develop evaluation and prompt-testing frameworks to measure agent accuracy, reliability, quality, and performance.
- Support deployment, monitoring, troubleshooting, and continuous improvement of AI agents and LLM applications.
- Ensure AI solutions comply with enterprise security, governance, compliance, and responsible AI standards.
- Participate in architecture reviews and technical design documentation.
- Collaborate with product, architecture, engineering, security, and business teams.
Required Qualifications
- 6+ years of overall IT/software engineering experience.
- Hands-on experience working with Generative AI and Large Language Models.
- Strong experience with prompt engineering and prompt optimization.
- Experience developing Agentic AI applications and autonomous AI agents.
- Experience with LangChain, LangGraph, Semantic Kernel, AutoGen, CrewAI, or comparable agent frameworks.
- Hands-on experience with MCP, MCP servers, MCP tools, or AI tool integration.
- Strong understanding of agent planning, reasoning, memory, context management, and tool calling.
- Experience building production RAG pipelines.
- Experience with vector databases, embeddings, semantic search, and knowledge retrieval.
- Strong programming experience with Python, TypeScript, or similar languages.
- Experience integrating REST APIs, enterprise applications, databases, and external tools.
- Experience with cloud-based AI platforms such as AWS Bedrock, Azure OpenAI, Azure AI Foundry, or Google Vertex AI.
- Understanding of LLM evaluation, monitoring, security, governance, and responsible AI practices.
- Strong analytical, problem-solving, communication, and collaboration skills.
Preferred Qualifications
- Experience building enterprise copilots, AI assistants, or autonomous agent ecosystems.
- Experience with multi-agent orchestration and complex AI workflow automation.
- Experience developing custom AI plugins or tools.
- Experience with AI evaluation and observability frameworks.
- Experience integrating AI solutions with healthcare systems, health records, or other regulated-industry platforms.
- Understanding of enterprise security and compliance requirements for Generative AI applications.
Key Skills
Agentic AI, Generative AI, Prompt Engineering, Large Language Models, LLM, AI Agents, Autonomous Agents, MCP, Model Context Protocol, MCP Server, MCP Tools, LangChain, LangGraph, Semantic Kernel, AutoGen, CrewAI, RAG, Retrieval Augmented Generation, Vector Database, Embeddings, Semantic Search, Tool Calling, Agent Orchestration, Multi Agent Systems, Context Management, Prompt Optimization, Python, TypeScript, OpenAI, Azure OpenAI, Azure AI Foundry, AWS Bedrock, Google Vertex AI, REST API, AI Governance, Responsible AI, LLM Evaluation