Agentic AI Engineer (New York City Metropolitan Area)

Job Title: Agentic AI Engineer

Experience: 8–10 Years

Employment Type: Long term Contract

Location: NY/NJ/TX

Job Summary

We are seeking experienced AI Engineers / Agentic AI Engineers with strong hands-on expertise in building enterprise-grade Generative AI, Agentic AI, RAG, and LLM-powered applications .

The ideal candidate will combine strong Python/software engineering skills with practical experience developing AI agents, multi-agent workflows, retrieval systems, Model Context Protocol (MCP) integrations, APIs, and cloud-based AI solutions.

This is a hands-on engineering role focused on taking AI solutions from prototype through production deployment .

Key Responsibilities

• Design, develop, and deploy production-grade Generative AI and Agentic AI applications .
• Build AI agents and multi-agent workflows involving reasoning, planning, tool usage, function calling, memory, and workflow automation.
• Develop and optimize RAG (Retrieval-Augmented Generation) solutions using enterprise structured and unstructured data.
• Design and implement integrations using Model Context Protocol (MCP) to enable AI agents to securely interact with enterprise tools, APIs, applications, databases, and data sources.
• Develop and integrate MCP servers, clients, tools, and resources for Agentic AI applications.
• Build AI orchestration workflows using frameworks such as LangGraph, LangChain, Microsoft Semantic Kernel, Microsoft Agent Framework, AutoGen, CrewAI , or equivalent.
• Integrate applications with LLMs such as OpenAI/Azure OpenAI, Anthropic Claude, Google Gemini, Llama , and other commercial or open-source models.
• Implement prompt engineering, embeddings, vector search, retrieval, reranking, context management, structured outputs, and tool/function calling .
• Build backend AI services and REST APIs using Python, FastAPI, Flask, Django , or similar technologies.
• Integrate AI solutions with enterprise applications and external services through APIs, databases, messaging systems, and MCP.
• Work with vector databases and search technologies such as Azure AI Search, Pinecone, Weaviate, FAISS, Chroma, OpenSearch, pgvector , or equivalent.
• Design and deploy AI solutions on Azure, AWS, or Google Cloud Platform (GCP) .
• Implement LLM evaluation, observability, monitoring, guardrails, security, and responsible AI practices .
• Optimize AI applications for performance, scalability, reliability, latency, and cost.
• Collaborate with product, engineering, architecture, data, and business teams to translate business use cases into scalable AI solutions.

Required Qualifications

• 8–10 years of overall experience in Software Engineering, Data Engineering, Machine Learning, or AI Engineering.
• Strong hands-on programming experience with Python .
• Strong recent experience developing Generative AI / LLM-powered applications .
• Hands-on experience building Agentic AI solutions or AI agents .
• Strong experience implementing RAG architectures and retrieval pipelines .
• Practical experience with Model Context Protocol (MCP) and agent-to-tool/application integrations.
• Experience with at least one AI orchestration/agent framework such as LangGraph, LangChain, Semantic Kernel, Microsoft Agent Framework, AutoGen, CrewAI , or equivalent.
• Experience working with OpenAI/Azure OpenAI, Anthropic Claude, Gemini, Llama , or similar LLMs.
• Strong understanding of prompt engineering, embeddings, vector search, tool/function calling, structured outputs, retrieval, reranking, and context management .
• Experience developing APIs and integrating AI solutions with enterprise applications and data sources.
• Hands-on experience with at least one major cloud platform: Azure, AWS, or GCP .
• Strong understanding of software engineering practices including Git, CI/CD, testing, debugging, and production deployment .

Preferred Qualifications

• Experience designing MCP servers and clients and exposing enterprise APIs, tools, or data through MCP.
• Experience developing multi-agent architectures and agent orchestration workflows .
• Knowledge of LLM evaluation, tracing, observability, and guardrails .
• Experience with AI security and responsible AI practices.
• Experience with Docker and Kubernetes .
• Familiarity with MLOps / LLMOps practices.
• Experience with fine-tuning, model customization, or open-source LLMs.
• Experience deploying enterprise-scale AI solutions into production.