Sr AI Engineer, Agentic Systems

Overview

Senior engineer role on Rubrik's Enterprise AI Incubation team, building production agentic systems that carry real enterprise workflows end to end.

What you'll do

• Lead product discovery with Product Managers and domain experts to map real workflows 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 carry real work and make decisions, including orchestrators, workers, monitoring agents, and coordinated agents with shared state and clear handoffs.
• Engineer agents for autonomy with reliability, including tool and orchestration flows, context management, caching, retries, and failure handling.
• Leverage full-stack engineering across backend services, APIs, data models, interactive screens, approval UIs, and chat interfaces.
• Apply solid software engineering practices to AI systems, treating prompts, skills, configs, and specs as versioned artifacts, with code review, tests, CI/CD, and staged rollouts.
• Implement evaluation, guardrails, and quality control, including derived evals, quality gates, human-in-the-loop approvals, and production monitoring.
• Use measured results to decide how to evolve or retire agents, and turn successful systems into reusable patterns and libraries.

What you'll need

• 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, including backend APIs and integrations, data models, and user-facing interfaces such as approval UIs, dashboards, or chat surfaces.
• Builder mindset: comfortable defining baselines and metrics, reporting results in business terms, and working in a fast-moving environment.
• System design skills: breaking down complex problems, designing APIs and data models, reasoning about latency, throughput, and failure modes.
• Algorithms, data structures, access control permissions, and data provenance.
• Spec-driven development: turning vague requirements into clear problem statements and design docs, using a Spec → Plan → Task → Code → Converge flow.
• Execution discipline: version control, code review, automated tests, CI/CD, staged rollouts and rollbacks, logging, metrics, and tracing.
• Building agents in code using LLM APIs, SDKs, and libraries, with shipped agentic systems that real users rely on.
• Designing robust agent harnesses and multi-agent orchestrations, managing tools, resources, context, and state under real-world data and load.
• Establishing continuous evaluation and safety mechanisms, turning production failures into test cases and gating changes on eval results.
• Clear judgment on AI fit: deciding when a problem needs an agent versus a simpler automation or no build, using data to make tradeoffs.

Nice to have

• Knowledge/context graphs: entities and relationships, GraphRAG, hybrid retrieval.
• Agent frameworks and runtimes such as Google ADK, LangGraph, OpenAI-style, or cloud or container platforms.
• Backend in Python, FastAPI, or similar stacks.
• Tools integration: MCP, Slack or Teams bots, REST APIs, webhooks.
• Data systems: Snowflake, Salesforce, graph stores.
• UX: conversational flows, chat surfaces, guided forms, simple dashboards for agent output.

Details

• Location: Bengaluru, India.