Senior AI Engineer, Agentic Systems

Rubrik•Palo Alto, CA

14h•$188,500 - $282,700

About The Position

Rubrik’s Enterprise AI Incubation team builds and operates AI-powered applications that transform how Rubrik works. The team develops systems that learn from company data, take action through agents, and improve over time, with executive backing to drive large-scale enterprise transformation. The Senior AI Engineer owns agent systems end to end: understanding workflows, designing architectures, writing code, deploying systems, and operating them in production. The role involves building production-grade infrastructure around model endpoints, including custom tooling, context pipelines, automated evaluations, and defensive guardrails for resilience with unstructured real-world data. The engineer determines whether a problem calls for an agent, simpler automation, or no build, and can stop or re-scope work that is unlikely to deliver impact. The engineer partners with product managers and domain experts to discover and map workflows, define problems and success criteria, and build production agents, automations, and internal tools. Solutions may include multi-agent workflows that coordinate decisions and business processes, delivered through backend services, APIs, data models, interactive screens, approval interfaces, and chat experiences. The role applies software engineering discipline to AI systems, establishes evaluations and human-in-the-loop controls where appropriate, monitors production results, and turns successful systems into reusable patterns and libraries.

Requirements

Around 7 or more years of professional software engineering experience in production systems.
Around 2 or more years of professional, hands-on experience building AI agents and agent-powered production applications with measurable outcomes.
Strong full-stack engineering background and a track record of designing, building, and owning services end to end, including backend APIs and integrations, data models, and user-facing interfaces.
Experience building agents in code using LLM APIs, SDKs, and libraries, and shipping agentic systems relied on by real users.
Ability to design robust agent harnesses and multi-agent orchestrations, model tools and resources, manage context and state, and maintain reliability with real-world data and load.
Ability to establish continuous evaluation and safety mechanisms, convert production failures into test cases, gate changes on evaluation results, and enforce workflow guardrails.
Sound judgment about when to use an agent, simpler automation, or no build, and ability to make data-informed tradeoffs involving model choice, latency, cost, context strategy, and autonomy.
System design skills, including breaking down complex problems, designing APIs and data models, reasoning about latency, throughput, and failure modes, and choosing simple, robust architectures.
Knowledge of algorithms, data structures, access-control permissions, and data provenance.
Ability to translate vague requirements into clear problem statements and design documentation, and to use a traceable Spec → Plan → Task → Code → Converge workflow, including with AI coding agents.
Execution discipline using version control, code review, automated tests, CI/CD, staged rollouts and rollbacks, logging, metrics, tracing, and production feedback.
Builder mindset, comfort defining baselines and metrics, reporting results in business terms, and working in a fast-moving environment.

Nice To Haves

Knowledge of context graphs, entities and relationships, GraphRAG, and hybrid retrieval.
Experience with agent frameworks and runtimes such as Google ADK, LangGraph, OpenAI-style frameworks, and cloud or container platforms.
Experience with Python, FastAPI, or similar backend stacks.
Experience integrating tools such as MCP, Slack or Teams bots, REST APIs, and webhooks.
Experience with Snowflake, Salesforce, and graph stores.
Experience building conversational flows, chat interfaces, guided forms, or simple dashboards for agent output.

Responsibilities

Lead product discovery with product managers and domain experts to understand workflows, map them, and define problems, baselines, and success criteria.
Design, build, test, and deploy production agents, automations, and internal tools using coding agents, LLM APIs, and agent frameworks integrated with Rubrik’s internal agent platform and business systems.
Turn complex processes into multi-agent workflows that perform work and make decisions, including orchestrators, worker agents, monitoring agents, and coordinated workflows across business functions.
Engineer reliable autonomous agents, including tool and orchestration flows, context management, caching, retries, and failure handling.
Use full-stack engineering to deliver agent systems through backend services, APIs, data models, interactive screens, approval UIs, and chat interfaces.
Apply software engineering practices to prompts, skills, configurations, and specifications, including versioning, code review, tests, CI/CD, and staged rollouts.
Develop evaluations and quality controls from workflow data, establish quality gates and guardrails, add human approvals when needed, and monitor production runs to improve agents.
Use measured outcomes to evolve or retire agents and turn successful systems into reusable patterns and libraries.
Define baselines and metrics, report results in business terms, and iterate by building, demonstrating, learning, and improving.