Agentic AI Engineer Multi-Agent LLM Architect

Location: Dallas, TX (Hybrid)

Duration: 12+ Months

Interview Process: Technical Screening + Final In-Person Interview (Mandatory)

Compensation: Depends on Experience, Skills. We are seeking an experienced AI Engineer with strong expertise in Agentic AI, Large Language Models (LLMs), and AI orchestration frameworks to design and develop enterprise-grade AI applications. The ideal candidate will have hands-on experience building multi-agent systems, conversational AI solutions, and production-ready LLM applications using modern AI frameworks and cloud technologies. This role requires a strong software engineering background with practical experience in AI orchestration, machine learning integration, prompt engineering, and LLMOps.

Responsibilities: Design, develop, and deploy agent-based AI applications using LangGraph, LangChain, and similar orchestration frameworks. Build scalable multi-agent workflows with intelligent task planning, execution, and state management. Develop reusable tools, workflows, and orchestration components for enterprise AI applications. Design and integrate Model Context Protocol (MCP) clients and tool ecosystems. Build conversational AI applications with contextual memory, reasoning, and dynamic tool invocation. Develop and integrate REST APIs and external enterprise systems into AI workflows. Integrate machine learning models using TensorFlow, PyTorch, or Scikit-learn for inference, prediction, and feedback loops. Implement Retrieval-Augmented Generation (RAG), vector search, and knowledge retrieval solutions where applicable. Apply LLMOps best practices including prompt engineering, prompt versioning, evaluation, monitoring, logging, observability, and performance optimization. Define and execute testing strategies for AI applications, including unit testing, workflow validation, scenario simulation, regression testing, and agent behavior evaluation. Optimize AI systems for scalability, reliability, security, and cost efficiency. Collaborate with engineering, product, and business teams to deliver enterprise AI solutions. Stay current with emerging technologies, frameworks, and best practices in Agentic AI and Generative AI.

Required Qualifications: Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Machine Learning, Data Science, or a related field.5+ years of software engineering experience.2+ years of hands-on experience developing Generative AI or LLM-based applications. Strong experience with LangGraph, LangChain, or similar AI orchestration frameworks. Experience designing and implementing multi-agent AI systems. Experience with Model Context Protocol (MCP) or similar tool integration architectures. Strong understanding of LLM architecture, prompt engineering, function calling, tool usage, memory management, and agent orchestration. Hands-on experience with Python. Experience with TensorFlow, PyTorch, or Scikit-learn. Experience building REST APIs and microservices. Experience working with cloud platforms such as AWS, Azure, or GCP.Experience deploying AI applications into production environments. Strong problem-solving and communication skills.

Preferred Qualifications: Experience with CrewAI, AutoGen, Semantic Kernel, or similar frameworks. Experience with vector databases such as Pinecone, Weaviate, Chroma, Milvus, or FAISS.Experience implementing RAG architectures. Familiarity with LangSmith, Weights & Biases, Arize AI, or other LLM observability platforms. Experience with Docker, Kubernetes, CI/CD, and cloud-native deployments. Knowledge of distributed systems and scalable AI architecture.