About Rabbit

Rabbit is a GCP cost-optimization and automation platform that helps enterprises make BigQuery and other GCP workloads truly cost-efficient. We combine deep platform intelligence, automation, and generative AI to turn cost insights into action.

The Challenge: AI has the potential to transform how infrastructure is managed, but most companies are still figuring out how to use LLMs beyond chatbots. We're building truly agentic systems that autonomously optimize cloud infrastructure — safely, intelligently, and at scale.

Role Overview

If you're excited about AI, but tired of building demos — this is your role.

Rabbit is evolving into a proactive cost optimization platform — a system that doesn't just recommend, but acts. We're looking for a Senior LLM / Agentic Engineer to pioneer AI-powered automation capabilities that help enterprises reduce cloud costs intelligently and safely.

The opportunity: This is the frontier of LLM applications. Not chatbots. Not summaries. Real autonomous agents that analyze petabytes of cost data, identify optimization opportunities, and implement changes to production infrastructure. You'll research, design, and implement LLM-driven features that turn cost insights into automated actions — and you'll do it first.

In our startup environment, you're not just implementing someone else's AI strategy — you're inventing it. Your experiments with prompt engineering, function calling, and agent architectures will directly shape the product. If you're ambitious, curious about AI's potential, and ready to push beyond what's been done before, this is where you belong.

What You'll Do

• Research, design, and implement AI-powered features that deliver automated cost optimization capabilities
• Build LLM-driven systems that transform cost insights into intelligent, actionable recommendations
• Develop safe and secure AI integration patterns that respect customer data boundaries and GCP security models
• Collaborate with the Application Architect to embed AI capabilities into Rabbit's backend architecture
• Experiment with emerging AI technologies and techniques to solve complex cost optimization challenges
• Ensure AI systems are accurate, reliable, and production-ready
• Continuously improve the effectiveness and safety of AI-powered automation features

What We're Looking For

• 5+ years in backend or applied ML engineering, with at least 1–2 years hands-on with LLM APIs (OpenAI, Vertex AI, Anthropic)
• Strong Python skills and experience with frameworks such as LangChain, LlamaIndex, or Vertex AI Agents
• Understanding of structured output generation, function calling, and API tool integration
• Familiarity with GitHub Actions / REST APIs and CI/CD automation
• Experience building or deploying production LLM systems (not just prototypes)
• Bonus: knowledge of cloud cost management or GCP optimization concepts

Why Join Rabbit

For AI engineers who want to build the future, not just talk about it:

• Ship real AI agents, not demos: Your work will go to production, managing real infrastructure for Fortune 500 companies. No more "this is just a prototype" — you'll build production-grade agentic systems that customers trust with their infrastructure
• Define the category: We're pioneering AI-driven infrastructure automation. There's no playbook. You'll help write it — through research, experimentation, and production deployments that push the boundaries of what LLMs can do
• Technical freedom meets real impact: Experiment with latest models (GPT-4, Claude, Gemini), try new architectures, research novel approaches — and when something works, ship it. Your ideas have a direct path to production
• Solve genuinely hard problems: Building autonomous agents that safely modify production infrastructure at scale, ensuring reliability while pushing automation boundaries — these are challenges worthy of your best work
• Learn at the cutting edge: Work with senior engineers who are as excited about AI's potential as you are. Collaborate with data architects who understand the domain deeply. Level up faster than you thought possible

Not for everyone. Perfect for you if: You're less interested in AI hype, more interested in AI reality. You want to build systems that work, not just impress at demos. You're ready to pioneer something genuinely new.