Software Engineer - Ruby AI

Rubrik Job Board•Palo Alto, CA

1d•Hybrid

About The Position

You'll design and build AI agents that help customers manage and protect their data through conversation instead of complex UIs. You'll work primarily in Python and Go, covering the full agent lifecycle: behavior design, tool integration, evaluation, and production observability. This is a hybrid role based in Palo Alto with deep ownership in a fast-moving product area. Ruby ships to thousands of enterprise customers who depend on it daily. You'll own production agents working at the intersection of large language models, enterprise security, and product design with a small team where your contributions are directly visible to company leadership.

Requirements

BS in Computer Science or equivalent field of study.
3+ years of professional software engineering experience.
Strong proficiency in Python with experience building production services.
Experience in at least one additional programming language (such as Go, Java, or C++).
Experience building AI-powered applications or working with AI/ML technologies.
Experience building and consuming APIs (GraphQL, gRPC, or REST) with solid engineering fundamentals in design, testing, and debugging.
Clear written and verbal communication skills, comfortable navigating ambiguity in a cross-team environment.

Nice To Haves

Experience with agent frameworks (LangChain, LlamaIndex, or similar) or RAG and vector search pipelines.
Experience with cloud platforms and containerized deployments (Docker, Kubernetes).
Familiarity with frontend technologies (React, TypeScript) for contributing to user-facing components.

Responsibilities

Build AI agents that resolve real customer problems (vSphere troubleshooting, cluster diagnostics, log analysis), reducing resolution time from hours to minutes.
Design tool integrations that let agents safely query data, retrieve logs, and perform operations while honoring RBAC and security boundaries.
Build retrieval pipelines and multi-model orchestration to deliver reliable, cost-effective agent responses across LLM providers.
Develop evaluation frameworks that measure agent quality and catch regressions before changes reach production.
Instrument agents with observability tooling and turn monitoring data into continuous quality improvements.