AI Engineer – LLMs, Agentic Workflows & MCP

International Logic Systems, Inc. is building and deploying next-generation AI solutions that connect large language models with agentic workflows, enterprise integrations, and retrieval-based knowledge. As an AI Engineer in a hybrid setup from Fairfax, VA, you will design, develop, and operate LLM-powered applications and the backend services that support them across cloud platforms and business use cases.

What you’ll work on

• Design, develop, and implement agentic AI systems that can reason, plan, and execute tasks using LLMs.
• Build MCP integrations to connect AI agents with tools, APIs, and enterprise systems.
• Develop, deploy, and maintain LLM-powered applications including AI copilots, conversational systems, and intelligent automation tools.
• Create prompt pipelines, tool-calling workflows, and multi-step reasoning systems for complex business scenarios.
• Develop backend services using Java (Spring Boot) and/or Python to expose AI capabilities through secure, scalable APIs.
• Use Spring AI or similar frameworks to integrate LLM capabilities into enterprise applications.
• Implement Retrieval-Augmented Generation (RAG) pipelines using vector databases and enterprise knowledge sources.
• Integrate AI solutions with cloud-native services and platforms, including AWS, Microsoft Azure, and Google Cloud.
• Deploy and maintain AI services with attention to scalability, reliability, security, and performance.
• Collaborate with cross-functional teams in an Agile/Scrum environment to deliver AI-powered solutions.
• Monitor, evaluate, and optimize AI systems for latency, cost efficiency, accuracy, and output quality.

Core requirements

• Bachelor’s degree in Computer Science, Engineering, or a related field.
• 5–9 years of professional experience in software engineering, AI engineering, or applied machine learning roles.
• Hands-on experience working with LLM APIs to build AI-powered applications.
• Experience designing and implementing agent-based workflows and agentic AI systems.
• Strong understanding of prompt engineering, tool calling, and structured outputs.
• Familiarity with RAG architectures and vector databases.
• Experience with MCP or similar standards for integrating AI agents with external tools and enterprise systems.
• Experience with at least one major cloud platform and exposure to others, including:
  • AWS (Lambda, Bedrock, SageMaker, S3)
  • Microsoft Azure (Azure OpenAI, Azure Functions, Cognitive Services)
  • Google Cloud (Gemini Enterprise Agent Platform, Vertex AI, Cloud Functions, BigQuery)

Technologies you may use

LLMs, Model Context Protocol (MCP), Java, Spring Boot, Python, Spring AI, RAG, vector databases, AWS, Lambda, Bedrock, SageMaker, S3, Microsoft Azure, Azure OpenAI, Azure Functions, Cognitive Services, Google Cloud, Gemini Enterprise Agent Platform, Vertex AI, Cloud Functions, BigQuery, Docker, React, Angular, REST APIs, microservices.

Preferred skills

• Strong programming skills in Python and/or Java.
• Experience developing backend services using Spring Boot, including REST APIs and microservices.
• Familiarity with Spring AI or similar frameworks for integrating LLM capabilities into Java applications.
• Experience with Docker and containerized deployments.
• Basic frontend development experience with React and/or Angular for AI-powered applications.
• Experience working in regulated environments, such as government, financial services, or healthcare.

Work arrangement

• Job type: Full-time
• Location: Fairfax, VA 22033
• Hybrid work: 2 days onsite per week at the ILS headquarters
• Location requirement: Must be local to the Washington, DC metropolitan area