Principal AI Software Engineer, Agentic Platform
Rapid7 is seeking a Principal AI Software Engineer to join the team building the Agentic Platform, Rapid7's next-generation security platform, where AI agents find the exposures that matter, remediate or mitigate them within customer policy, and prove the risk was reduced.
This role is for a deeply hands-on engineer with production experience of LLM agents and distributed systems who wants to work on some of the hardest open problems in autonomous security remediation, as part of an existing senior technical team.
About the Team
The Agentic Platform engineering team is building Rapid7's next-generation security platform around a simple idea: a security task isn't finished when an action succeeds, it's finished when fresh evidence shows the risk went down. The platform connects exposure, threat and detection evidence in one shared model on a streaming lakehouse. When something changes, AI agents reason over it, decide whether to remediate or mitigate, plan the change across the affected assets and their dependencies, act through the tools customers already run within the guardrails they set, and then verify the outcome.
You'll join an established, senior team of AI, platform, data and security engineers, working alongside distinguished and principal engineers, that is already running its first end-to-end remediation loops. The work sits at the cutting edge of autonomous security remediation: event-driven agents, safe and reversible action in live customer environments, governed autonomy, and learning from verified outcomes.
About the Role
As a Principal AI Engineer, Agentic Platform, your primary responsibility will be to bring deep AI and systems expertise to the platform's agentic core, working with the existing technical leadership to take autonomous remediation from its first loops to production scale. Specifically, your focus will be to:
- Work with the platform's distinguished and principal engineers to evolve the architecture of the agentic loop, from the change that triggers an agent to the evidence that confirms a risk was reduced.
- Design and build the hardest parts of remediation reasoning: deciding between a fix and a mitigation, planning changes across assets and their dependencies, and respecting change windows, approvals and customer policy.
- Help make autonomous action safe and reversible, with plans that can be approved, executed, verified and rolled back, and an audit trail customers can trust.
- Bring rigour to agent quality, with evaluation that measures outcomes (did the exposure actually close?) as well as model output, and regression suites for prompts and models.
- Improve how agents use context, including exploitability and threat intelligence (e.g., KEV, EPSS), reachability and attack paths, and asset criticality and ownership.
- Contribute to the learning loop, so that verified outcomes improve future plans, prompts and policies.
- Tackle systemic latency, cost and reliability problems across agent runs, including model selection and routing, token spend, caching and provider failover.
- Write code, review designs and pair with engineers across teams, raising the technical bar by example rather than by mandate.
- Partner with Product and the wider engineering team on what to build next, surfacing technical constraints and opportunities early.
The skills and qualities you'll bring include:
- Bring 10+ years of software engineering experience, including significant time as a senior technical contributor on complex, high-scale distributed systems.
- Bring recent, hands-on experience building LLM-based agent systems in production, including tool use, planning, retrieval and context engineering, and evaluation.
- Demonstrate a clear point of view on the trade-offs in autonomous systems, such as autonomy versus control, reversibility, latency versus reasoning depth, and model capability versus cost.
- Hands-on experience with tools such as:
- Foundation model platforms such as Amazon Bedrock, and LLM gateways or routers (e.g., LiteLLM).
- Agent frameworks and protocols such as the Model Context Protocol (MCP), LangGraph, CrewAI or equivalent.
- Evaluation tooling for LLM systems, including golden datasets, LLM-as-judge and online quality metrics.
- Durable workflow engines such as Temporal, and event streaming such as Kafka or Flink.
- Write production-quality code in Python or Go, and care about testing, readability and operability.
- Show deep understanding of distributed systems and of designing for failure at scale in cloud-native environments (AWS and Kubernetes preferred).
- Experience with vulnerability or exposure management, patch and configuration management, or security orchestration and automated response is a strong plus.
- Experience with AI safety for agents, such as prompt-injection defences, sandboxed execution and least-privilege tool access, is a plus.
- Stay current with emerging AI research and technology, and turn it into practical, reliable product capability.
- Takes ownership of significant technical outcomes across multiple teams, proactively identifying and addressing risks, driving complex challenges to resolution and ensuring solutions deliver against agreed technical and customer objectives
- Strong communicator with the ability to explain technical trade-offs to engineering, product, and leadership audiences
- Builds strong cross functional partnerships across Engineering, Product, and other teams to align on technical direction and deliver shared outcomes
- Connects customer needs and business priorities to technical decisions, evaluating the value, cost and trade-offs of AI solutions to ensure investments deliver measurable customer and business outcomes
- Embody our core values to foster a culture of excellence that drives meaningful impact and collective success
We know that the best ideas and solutions come from multi-dimensional teams. That's because these teams reflect a variety of backgrounds and professional experiences. If you are excited about this role and feel your experience can make an impact, please don't be shy - apply today.

#LI-PB1
About Rapid7
At Rapid7, our vision is to create a secure digital world for our customers, our industry, and our communities. We do this by harnessing our collective expertise and passion to challenge what’s possible and drive extraordinary impact. We’re building a dynamic and collaborative workplace where new ideas are welcome.
Protecting 11,500+ customers against bad actors and threats means we’re continuing to push the envelope just like we’ ve been doing for the past 20 years. If you ’re ready to solve some of the toughest challenges in cybersecurity, we’re ready to help you take command of your career. Join us.
Required Skills
Required Languages
🇬🇧 English