Job Description & Details
This is a hands-on, highly technical role building advanced autonomous agent workflows and conversational systems in Charlotte, NC. If you are tired of building basic wrappers around LLMs and want to dive deep into multi-agent coordination, RAG, and production observability, this is worth a serious look.
What You'll Actually Be Doing
You'll spend your days architecting intelligent agent workflows, wiring up LLMs with external tools, and ensuring your systems actually behave deterministically. Expect to spend a lot of time debugging why an agent went off-rails, setting up evaluation frameworks to measure response accuracy, and implementing Model Context Protocol (MCP) servers to let your agents talk to each other seamlessly.
The Core Tech Stack
You need to know Python inside and out, paired with LangChain and modern agent frameworks like the Agent Development Kit (ADK). Strong RAG implementation skills are non-negotiable because your agents will need reliable context retrieval. Experience with PyTest for automated testing of non-deterministic outputs is also a major focus here.
Interview Expectations
The interviewers are definitely going to ask you how you handle infinite loops or hallucination cascades in autonomous multi-agent systems. They want to see that you understand how to build robust guardrails, set up strict evaluation metrics, and implement proper logging and observability using modern monitoring tools.
Application Advice
Make sure your resume screams 'Agentic AI' rather than just 'Machine Learning'. Highlight specific projects where you built RAG pipelines, integrated LangChain, or worked with Agent-to-Agent communication patterns, and make sure Python and PyTest are prominently featured to pass the automated resume screen.