Senior AI Engineer - Enterprise Agentic Systems

Rubrik Job Board · Bangalore, India · Engineering

Posted 2026-11-21

Apply for this role →

About the role

We are looking for a Senior AI Engineer to join Rubrik's Applied AI Apps org, building production-grade, full-stack applications and APIs for our internal Business teams while embedding AI-agentified capabilities into these internal platforms. This is a hands-on build role: you will own features end to end from database schema through backend services and distributed systems to the user interface and bring practical, hands-on experience building or integrating AI agents, tool-calling workflows along with the right AI evals or LLM-powered features into production systems that our business stakeholders rely on.

The ideal candidate combines strong full-stack engineering fundamentals with a systems mindset for reliability and scale, and has spent meaningful hands-on time (1–2 years) building AI-agentified applications not just experimenting with AI tools, but shipping agentic features in production. We are targeting 8+ years of overall software engineering experience; this is flexible for candidates who demonstrate strong depth across full-stack, distributed systems, and applied AI engineering skills during technical evaluation.

What you'll do

Key Responsibilities:

Build and productionize agentic workflows, LLM-powered automation, and AI-assisted tooling having hands-on experience with these systems.

Design and build end-to-end agent evaluation frameworks that measure correctness, latency, cost, safety, and task completion rate, including synthetic test environments that stress-test agents built on Google ADK and Google AI/ML services (Vertex AI, Gemini) under diverse real-world conditions.

Curate golden datasets and test harnesses for our Rubrik enterprise use cases and contribute to an eval-as-a-service platform that IT teams can self-serve against standard and custom benchmarks.

Automate regression and drift detection with CI/CD-integrated eval pipelines that catch regressions on every model or prompt change before production deployments

Architect for distributed systems concerns: scalability, fault tolerance, data consistency, and service boundaries across backend and data layers.

Build full-stack web applications and own features end to end be it database schema, backend services, APIs (REST, GraphQL, gRPC, and webhooks), and frontend (React/Next.js) user interface

Design and build APIs and services that are consumed by applications, internal tools, and AI agents/LLMs, including tool-calling interfaces

Apply reliability engineering practices — observability (logging, metrics, tracing), SLAs/SLOs, incident response, and post-incident reviews — to keep production systems healthy.

Clarify requirements upfront, surface blockers early, and communicate progress proactively without being asked.

Collaborate openly with internal Business stakeholders, Product, QA, DevOps, and UX or designer teams; avoid working in silos.

Experience you'll need

Bachelor's degree in Computer Science, Information Systems, or a related field.

5-7 years of Salesforce experience.

Strong knowledge of Salesforce Sales Cloud, Marketing Cloud (or Pardot), Channel/Partner Portals, and Salesforce Admin functionalities.

Experience with Salesforce Service Cloud and Case Management is a plus.

Proficiency in troubleshooting complex issues involving Apex, Flows, Workflows, Process Builder, Validation Rules, Reports & Dashboards.

Familiarity with Salesforce integration tools (e.g., MuleSoft, Zapier, Marketing Automation Platforms).

Salesforce Administrator certification is required; additional certifications (e.g., Platform App Builder, Marketing Cloud Administrator, Marketing Cloud Email Specialist) are a plus.

Required Qualification

Education & Experience

Bachelor's or Master's degree in Computer Science, Engineering, or equivalent practical experience.

8+ years of hands-on software engineering experience across full-stack engineering (flexible based on demonstrated strength in technical evaluation).

1–2 years of hands-on experience building, integrating and operating AI Agent powered applications (agentic workflows, tool-calling, RAG, LLM-powered features) in production..

Demonstrated experience owning systems designed for scale and reliability, not just feature delivery.

Technical Skills — Applied AI Engineering

1–2 years of hands-on experience building AI applications, using agent frameworks (e.g., Claude Agent SDK, Google ADK, LangGraph, or equivalent).

Practical understanding of latency, cost, rate limiting, and safety/guardrails when exposing systems for AI consumption.

Experience with coding agents, Spec Driven and Eval Driven Development

Deep hands-on experience with LLM evaluation — familiarity with frameworks and libraries such as LangSmith, DeepEval, LLM as a Judge, Promptfoo, RAGAS, Hugging Face evaluation tooling, custom eval harnesses

Strong understanding of agentic AI patterns — Supervisor Multi-Agent, ReAct/Plan-Execute reasoning chains, retrieval-augmented generation (RAG)

Technical Skills — Full Stack Software Engineering

Frontend: Strong JavaScript fundamentals; hands-on experience with React and Next.js for building modern, production-grade web applications (hooks, state management, component architecture, routing, server-side rendering).

Backend: Proficient in Python, writing production-grade code; hands-on experience with FastAPI or Flask (or equivalent frameworks) for building REST APIs.

Database: Experience with relational and non-relational databases (PostgreSQL, MySQL, SQL Server, MongoDB, or equivalent); solid understanding of schema design, joins, indexing, and query optimization.

APIs: Secure API design, API Gateway expertise with platforms such as Kong / Apigee / AWS API Gateway / Azure APIM / MuleSoft API Gateway for routing, rate limiting, and policy enforcement.

Technical Skills — Distributed Systems & Reliability Engineering

Working knowledge of distributed systems concepts: service decomposition, consistency models, caching, queuing/messaging, and failure handling.

Reliability engineering fundamentals: observability (logging, metrics, tracing), SLAs/SLOs, error budgets, and operational runbooks.

Ability to reason about system design trade-offs and build scalable, resilient solutions under ambiguity.

Soft Skills

Proactive communication — shares updates without being asked and flags blockers early.

Asks the right questions — clarifies requirements upfront before jumping into implementation.

Ownership mindset — treats the project as their own rather than just completing tickets.

Transparency — speaks up when something is unclear instead of making assumptions.

Strong analytical mindset to break down complex or ambiguous problems.

Preferred Qualifications

Experience with agentic frameworks (ADK, LangGraph, or similar) beyond individual projects — production deployment experience preferred.

Familiarity with API documentation standards (Swagger/OpenAPI).

Basic DevOps awareness (Docker, CI/CD) and Git/version-control best practices.

Testing experience across unit and integration levels.

Experience with modern web app tooling — component libraries (e.g., Tailwind, MUI) and state management (e.g., Redux, Zustand).

Exposure to cloud-native development (AWS, Azure, or GCP), including containers and infrastructure as code.

Deep Learning/NLP Knowledge: Fundamental understanding of how LLMs work, including concepts like RAG, prompting, and the technical challenges related to alignment

Data Analysis: Experience with data analysis and visualization tools (e.g., Pandas, SQL) for analyzing evaluation and safety results

Apply for this role →

← Back to all jobs