Senior Agentic AI Engineer

Location: Reston, VA | Hybrid — 3 days onsite per week

Position Type: Contract | Duration: 11 months | Pay Rate: $59.35–$77.00 / Hour (USD) | Work Authorization: Applicants must be authorized to work for ANY employer in the U.S. (USC or Green Card holders only; sponsorship not available at this time).

About the role

We are seeking a highly skilled Senior Agentic AI Engineer to design, develop, and deploy modern Agentic AI solutions. This role focuses on building production-grade Generative AI applications, multi-agent workflows, and Retrieval-Augmented Generation (RAG) pipelines for enterprise use on Microsoft Azure. You will collaborate with architects, software engineers, data engineers, and business stakeholders to translate requirements into AI-powered software solutions. The ideal candidate brings hands-on experience developing, evaluating, and operating Agentic AI solutions, supported by strong front-end and back-end engineering fundamentals.

Responsibilities

• Build Generative AI & Retrieval-Augmented Generation LLM Applications
  • Build LLM-powered applications for text generation, summarization, Q&A, conversational AI, enterprise knowledge search, and multi-agent orchestration.
  • Develop advanced RAG pipelines using embeddings, Azure AI Search vector and hybrid retrieval, document chunking, metadata filtering, reranking, citations, and grounding techniques with enterprise data.
  • Build secure, reliable integrations between AI agents and enterprise tools, REST APIs, relational databases, and event-driven services.
  • Develop and maintain user-facing AI application experiences using React and TypeScript, and supporting application services using Node.js or comparable back-end technologies.
• AI Agents & Agentic Automation
  • Design and implement single-agent and multi-agent systems for intelligent automation, decisioning, and complex workflows.
  • Build autonomous and human-in-the-loop agents that plan, reason, act, and interact with tools, APIs, enterprise data, and event-driven systems.
  • Develop agentic workflows using Microsoft Agent Framework, Azure AI Foundry services, or comparable modern orchestration frameworks.
  • Implement configuration-driven agent behavior, prompt and tool management, authorization boundaries, and resilient error-handling patterns.
  • Define and automate evaluation approaches for agent quality, including groundedness, relevance, citation quality, safety, and regression testing.
  • Instrument agent workflows for traces, tool calls, latency, token usage, errors, and operational metrics using OpenTelemetry, Application Insights, or comparable observability platforms.
  • Build highly scalable, secure, containerized solutions with CI/CD, health checks, horizontal scaling, and production monitoring.

Requirements

• Strong software engineering background with experience designing and deploying production-grade cloud applications.
• Experience building front-end applications with React and TypeScript, and back-end services with Node.js or comparable application frameworks.
• Hands-on experience building Generative AI and RAG applications with Azure AI Foundry, Azure OpenAI, Azure AI Search, LLM APIs, embeddings, vector or hybrid search, knowledge retrieval, grounding, and citations.
• Experience with Agentic AI frameworks such as Microsoft Agent Framework, Semantic Kernel, LangGraph, AutoGen, or comparable orchestration frameworks; including single-agent and multi-agent systems, tool-calling workflows, and human-in-the-loop controls.
• Experience evaluating and improving agent quality, including prompt engineering, test datasets, LLM-based evaluation, safety checks, and production feedback loops.
• Strong knowledge of LLMOps, CI/CD, containerization (Docker and Kubernetes), observability, and production operations for AI applications.
• Good understanding of RESTful API principles, asynchronous application patterns, secure integrations, relational databases, SQL, and data-access patterns; familiarity with SQL/NoSQL data stores and data engineering or ETL pipelines.
• Experience working in an enterprise environment with large-scale, secure AI deployments, including identity, authorization, data privacy, compliance, and production monitoring.
• Strong analytical, problem-solving, collaboration, and communication skills.

Qualifications

• Bachelor's degree (or international equivalent) required.
• 8 years of relevant software engineering experience.
• 2–3 years of hands-on Generative AI, LLM application, or Agentic AI solution development experience.

Benefits

• Medical, Vision, and Dental Insurance Plans
• 401k Retirement Fund

About the Client

This client is a trusted engineering and project management partner operating across the energy, infrastructure, and nuclear sectors, delivering some of the world's most complex infrastructure projects across 160 countries on all seven continents. With more than 125 years of history and over 25,000 completed projects, the organization works at exceptional scale for national governments, global energy companies, and the world's largest public agencies. Teams here include civil and structural engineers, project controls specialists, procurement managers, nuclear and environmental remediation professionals, and — increasingly — engineers and technical professionals driving AI-powered solutions across its global portfolio.

About GTT

GTT is a minority-owned staffing firm and a subsidiary of Chenega Corporation, a Native American-owned company in Alaska. We highly value diverse and inclusive workplaces and support Fortune 500 organizations across banking, financial services, technology, life sciences, biotech, utilities, and retail sectors throughout the U.S. and Canada.