Full-Stack Engineer

Role Summary

We are seeking Full-Stack Engineers who operate "above the code." You will not just be writing software; you will be architecting and monitoring autonomous AI systems that write and execute code. The ideal candidate understands the mechanics of LLMs and can maintain system integrity when AI agents "go sideways".

Core Responsibilities

• Agent Deployment: Deploy and manage autonomous AI agents within cloud environments.
• Evaluation & Monitoring: Utilize frameworks like LangChain and LangGraph to monitor AI performance and spend.
• System Optimization: Perform context engineering and optimize for token usage.
• Drift Management: Identify and mitigate "drift" in AI models to ensure consistent, high-quality outputs.
• RAG Implementation: Implement and scale Retrieval-Augmented Generation (RAG) systems.

Technical Qualifications

• Full-Stack Expertise: Proficiency across the entire stack; traditional silos of front-end or back-end do not apply here.
• Polyglot Debugging: Ability to read and understand code in Python, TypeScript, and Java to oversee AI-generated outputs.
• Architectural Depth: Deep understanding of how to build with agents rather than just using them as a shortcut for basic coding.