Location: Dallas, TX
Duration: Long-Term Contract
2 rounds of In-person interview
Work Arrangement: Onsite – 4–5 days per week in the office
We are seeking an experienced Agentic AI Engineer to design, develop, and deploy enterprise-grade Generative AI and Agentic AI solutions. The ideal candidate will have strong hands-on experience building AI-powered applications using AWS Bedrock, Amazon Bedrock AgentCore, LangGraph, LangChain, Model Context Protocol (MCP), and Retrieval-Augmented Generation (RAG) architectures.
The candidate will be responsible for developing autonomous and multi-agent systems, implementing advanced AI orchestration workflows, integrating enterprise systems, and deploying scalable, secure, and production-ready AI applications on AWS.
This role requires a strong software engineering background combined with deep expertise in Generative AI, LLMs, agentic architectures, cloud infrastructure, and enterprise application development.
Design, develop, and deploy autonomous and multi-agent AI systems using AWS Bedrock AgentCore capabilities.
Build, orchestrate, and optimize AI agent workflows using LangGraph and LangChain.
Implement agent planning, reasoning, tool calling, memory management, and decision-making capabilities.
Design agent-to-agent communication and agent-to-system interaction patterns.
Implement Model Context Protocol (MCP) integrations and tool-calling architectures to connect AI agents with enterprise tools and services.
Build enterprise-scale Retrieval-Augmented Generation (RAG) solutions using AWS Bedrock foundation models and embedding models.
Design and optimize document processing, vectorization, indexing, semantic search, retrieval, re-ranking, and response-grounding strategies.
Develop prompt engineering frameworks, LLM evaluation methodologies, and techniques to improve AI application accuracy and reliability.
Build conversational AI applications, enterprise knowledge assistants, AI copilots, and intelligent automation solutions.
Integrate AWS Bedrock Guardrails and implement responsible AI practices to support security, compliance, and content safety.
Design and develop RESTful APIs to expose AI capabilities to enterprise applications and downstream systems.
Integrate AI agents with business applications, enterprise workflows, databases, APIs, and external systems.
Develop intuitive front-end experiences using React and modern UI frameworks.
Build scalable, reusable AI services and microservices following enterprise architecture standards.
Deploy and manage AI solutions on AWS using Infrastructure as Code (IaC) principles.
Develop and maintain cloud infrastructure using Terraform.
Implement and maintain CI/CD pipelines using GitLab.
Establish best practices, reusable components, development standards, and architectural patterns for Generative AI and Agentic AI implementations.
Collaborate with product owners, solution architects, data engineers, and business stakeholders to translate business requirements into AI-driven solutions.
Ensure AI applications meet enterprise security, governance, compliance, scalability, and responsible AI requirements.
Bachelor's or Master's degree in Computer Science, Engineering, Artificial Intelligence, Data Science, or a related field.
7+ years of software engineering experience, including significant experience developing AI/ML solutions.
4+ years of hands-on experience with Generative AI, Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG) architectures.
2+ years of experience designing and implementing Agentic AI applications or multi-agent systems.
Strong hands-on experience with AWS Bedrock and foundation model integrations.
Experience with Amazon Bedrock AgentCore and agent development capabilities.
Strong programming skills in Python and experience building production-grade AI applications.
Hands-on experience with LangGraph and LangChain for agent orchestration and workflow development.
Experience implementing MCP (Model Context Protocol), function calling, tool integration, and agent-to-system communication.
Strong understanding of RAG architecture, embedding models, vector databases, semantic search, and retrieval optimization.
Experience deploying and managing production-scale AI applications in cloud environments, preferably AWS.
Experience designing and developing RESTful APIs and integrating AI services with enterprise applications.
Working knowledge of React and modern front-end development frameworks.
Experience with Terraform and Infrastructure as Code (IaC).
Experience developing and maintaining CI/CD pipelines using GitLab.
Strong understanding of application security, cloud security, AI governance, and responsible AI principles.
Excellent problem-solving, communication, and collaboration skills.
Experience building enterprise AI copilots, conversational assistants, and intelligent automation solutions.
Experience implementing advanced agent orchestration and stateful workflows using LangGraph.
Experience with AI agent evaluation, testing, observability, and benchmarking frameworks.
Experience integrating knowledge graphs and implementing graph-based reasoning.
Experience designing and implementing Human-in-the-Loop (HITL) workflows for AI agents.
Knowledge of LLM performance optimization, response quality evaluation, latency reduction, and cost optimization.
Experience implementing enterprise-grade AI governance, monitoring, and operational best practices.
Experience designing scalable, modular, and reusable Generative AI and Agentic AI architectures.
Generative AI & LLMs: Generative AI, Large Language Models (LLMs), Prompt Engineering, Foundation Models, LLM Evaluation
Agentic AI: Agentic AI, Multi-Agent Systems, Autonomous Agents, Amazon Bedrock AgentCore, Agent Orchestration, Tool Calling, Agent Memory, Planning and Reasoning
AI Frameworks: LangGraph, LangChain
RAG & Knowledge Retrieval: Retrieval-Augmented Generation (RAG), Embeddings, Vector Databases, Semantic Search, Document Indexing, Re-Ranking, Grounding, Knowledge Graphs
AWS & Cloud: AWS Bedrock, AWS Cloud Services, Foundation Model Integration, Cloud-Native AI Applications
AI Integration: Model Context Protocol (MCP), REST APIs, Enterprise Integrations, Microservices
Application Development: Python, React, Front-End Development
DevOps & Infrastructure: Terraform, Infrastructure as Code (IaC), GitLab CI/CD, Cloud Deployment
AI Security & Governance: Bedrock Guardrails, Responsible AI, AI Safety, Security, Compliance, Governance
Location: Dallas, TX
Duration: Long-Term Contract
Work Arrangement: Onsite, 4–5 days per week
Experience Level: Senior / Experienced Professional
The ideal candidate is a hands-on AI engineer with a strong software development foundation and proven experience delivering production-ready Generative AI and Agentic AI applications. Candidates should be comfortable designing multi-agent architectures, building RAG pipelines, orchestrating workflows with LangGraph and LangChain, integrating MCP-based tools, and deploying enterprise AI solutions using AWS Bedrock and AgentCore.
Candidates must be willing to work onsite in Dallas, TX, 4–5 days per week.
