We're hiring an AI Engineer to build production-ready, agentic AI experiences on Google Cloud (Vertex AI) and OpenAI. You'll ship real features-agents, tools, and lightweight UIs-that plug into our data and internal systems to improve productivity across the company.
Key Responsibilities:
- Agentic development on Vertex AI: Build and iterate multi-step agents with Vertex AI (Agent Builder / Gemini), including tool use, memory, and evaluation loops.
- MCP & tool integrations: Implement Model Context Protocol (MCP) connectors and secure API integrations so agents can act on enterprise systems with least-privilege access.
- RAG & data grounding: Wire up retrieval (vector stores / embeddings), schema-aware prompts, and guardrails for accurate, auditable outputs.
- Vertex-based UI for agents: Prototype intuitive chat and task UIs (web or internal portals), including session history, tool invocation panels, and feedback widgets; embed agents into existing apps.
- Integration & Data Access: Connect AI agents with internal APIs and enterprise data (e.g., BigQuery or REST endpoints, or webhooks) using existing cloud tools.
- Quality & telemetry: Define success metrics (quality, latency, cost), add logging/observability, and run structured experiments to improve outcomes.
Requirements:
- 2-3 years in software/AI application engineering.
- Hands-on experience creating and deploying custom Gems (apps) within Gemini / Vertex AI Agent Builder, including configuration, grounding, and integration with enterprise data and APIs.
- Hands-on with Google Cloud (Vertex AI, BigQuery, Cloud Run/Functions) and at least one LLM API (OpenAI or Gemini Preferred).
- Experience building small end-to-end features: backend APIs, prompt/agent logic, and a basic UI to demo/ship.
- Familiarity with agent frameworks (e.g., LangGraph/LangChain) and patterns like tool use, planning, and memory.
- Working knowledge of RAG concepts (chunking, embeddings, retrieval), plus prompt testing and evaluation basics.
- Strong collaboration skills; comfortable partnering with security, data, and app teams to ship safely and fast.
Nice to Have:
- Exposure to GCP IAM, secrets management, and enterprise compliance considerations.
- Familiarity with Vertex AI Search, vector databases, or event/webhook architectures.
- Interest in emerging standards (MCP), responsible AI practices, and cost/perf optimization.
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 11,000+ 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.
Top Skills
What the Team is Saying
What We Do
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 11,000+ 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.
Why Work With Us
With our products, research, and open source communities, we’re building a secure digital future for everyone. This means constantly learning and evolving in an industry that’s anything but stagnant. You’ll be faced with tough challenges, and given the support to find creative solutions that drive our business, and your career forward.
Gallery
Rapid7 Offices
Hybrid Workspace
Employees engage in a combination of remote and on-site work.
Our default working model is hybrid, with employees working three days per week in the office. This approach underpins our commitment to flexibility and adaptability while supporting our dedication to development, teamwork and customer purpose.
