Principal LLM Engineer [19 / 10 / 2025]

Principal LLM Engineer

Join Rapid7 : Secure the Future with AI

Are you ready to lead the charge in integrating cutting-edge Large Language Models (LLMs) into world-class Cyber Security products?

Rapid7 is looking for a Principal LLM Engineer with a rare combination of deep Data Science expertise, mastery of production MLOps, and 13+ years of experience. You won't just build models; you'll architect the AI systems that protect our customers from the world's most sophisticated threats. This is a role for a proven leader who turns breakthrough research into scalable, high-impact security solutions.

What You'll Be Doing : Technical Leadership

As a Principal Engineer, you will define and execute the technical strategy across three critical domains :

1. LLM & AI System Architecture

You'll design and build the next generation of AI-powered security features.

• LLM Orchestration : Architect complex security applications using frameworks like LangChain and LangGraph to connect LLMs with our data and tools.
• RAG Pipelines : Build and optimise high-performance Retrieval-Augmented Generation (RAG) systems using Vector DBs to give our AI the context it needs from vast security datasets.
• Model Optimisation : Implement efficient adaptation techniques (LoRA / PEFT) and run rigorous evaluation using tools like Promptfoo / HELM to ensure model accuracy and safety.
• Governance & Safety : Design and enforce security Guardrails and governance policies for all LLM deployments.

2. Security-Focused MLOps & Production

You'll ensure our AI is always live, stable, and fighting threats.

3. Data Science & Security Foundation

Your background will enable you to solve complex security problems with data.

What You'll Bring

If you thrive on solving the hardest problems in AI and applying that power to make the world a safer place, we want to hear from you!