About the Role
We're building AGS's AI Engineering team from the ground up, and we're hiring engineers at the start of their careers who want to build real AI systems—not tinker with demos. As a AI Solutions Engineer I, you'll write code that ships to production, contributing to intelligent agents, agentic workflows, and the reusable Foundation Layer capabilities that power them.
This is a learning-intensive role with real responsibility. You'll pair with senior engineers and the Lead, participate in code reviews, and build working features from day one. We don't expect you to know LLMs or the Microsoft ecosystem yet—we expect strong software engineering fundamentals and the drive to learn fast. If you can write clean code, reason about problems clearly, and take feedback well, we'll invest in your growth.
We hire engineers, not configuration specialists. If you want to write real software that solves real problems using AI, this is where to start.
Responsibilities
Build & Deliver
- Develop features for intelligent agents, conversational interfaces, and agentic workflows
- Implement components of Foundation Layer services under guidance from senior engineers
- Write integrations between AI capabilities and enterprise systems (M365, Dataverse, external APIs)
- Write clean, tested code that follows team patterns and standards
- Fix bugs, investigate issues, and improve existing solutions
Learn & Grow
- Pair program with senior engineers and the Lead to learn architecture patterns and best practices
- Participate actively in code reviews—ask questions, give thoughtful feedback, and apply what you learn
- Build understanding of our technology stack: Semantic Kernel, Azure, Microsoft 365, LLMs
- Develop skills in prompt engineering, RAG patterns, and agent design through hands-on work
- Take on progressively more complex work as your skills develop
Engineering Practices
- Write unit and integration tests for your code
- Follow CI/CD practices and contribute to build and deployment processes
- Document your work—what you built, why, and how it works
- Monitor deployed solutions and participate in incident response
Collaboration
- Work with AI Solutions Analysts to understand requirements and ask clarifying questions
- Communicate progress, blockers, and what you're learning to your team
- Participate in sprint ceremonies and contribute to planning discussions
- Support QA by clarifying implementation details and fixing defects
