Agentic Engineer

Integral

14d

About The Position

At Integral Federal, we invest in our people—equipping them with the tools, expertise, and culture of innovation needed to deliver measurable results. Committed to exceeding expectations and delivering mission impact, our team thrives on solving complex challenges, optimizing performance, and ensuring long-term success for our clients. The Role: We are looking for a curious builder to join our team and develop AI Agents. You will design, build, and deploy autonomous agents and LLM-powered applications across AWS, Google Cloud, and Microsoft Azure. We do not require a Master’s degree, a Bachelor’s degree, or any degree at all. We care about your understanding of modern AI architectures and your drive to repetitively solve problems. If you are the type of developer who loves tinkering with multi-agent workflows, experimenting with the Model Context Protocol (MCP), and testing the limits of new foundation models, you belong here.

Requirements

Proof of Capability: Personal projects, GitHub repositories, or open-source contributions demonstrating your ability to build AI apps or agents. (Please include links in your application).
LLM & Agent Experience: Hands-on experience working directly with LLM APIs (OpenAI, Anthropic, Gemini, etc.) and building agentic loops (tool calling, memory management, reasoning).
Protocol Knowledge: Familiarity with or a strong desire to master the Model Context Protocol (MCP) for tool integration.
Cloud Fluency: Experience deploying applications or running experiments on at least one major cloud provider (AWS, GCP, or Azure) and a willingness to learn the others.
Builder’s Mindset: An insatiable curiosity, a high tolerance for ambiguity, and the grit to troubleshoot novel problems.

Nice To Haves

Experience fine-tuning models or working with local, open-weight models.
Experience testing models to create a baseline and identify drift
Experience building custom tools, robust RAG pipelines, or complex data ingestion pipelines from scratch.

Responsibilities

Design and build autonomous AI agents using the latest large language models (LLMs) and orchestration frameworks.
Implement and leverage the Model Context Protocol (MCP) to seamlessly connect our AI models with external tools, APIs, and data sources.
Move beyond prototypes by building rigorous evaluation (Evals) pipelines and implementing LLM observability to ensure agents run reliably without hallucinating or getting stuck in infinite tool-calling loops.
Deploy AI solutions across multi-cloud environments, utilizing the best tools available on AWS, Google Cloud (GCP), and Microsoft Azure.
Translate complex, ambiguous problems into functional, robust, production-ready code.
Stay plugged into the bleeding edge of the AI landscape, bringing new tools, papers, and open-source projects to the team's attention.
Work closely with other engineers to securely and efficiently integrate agentic workflows into our existing infrastructure.