Backend Engineer, AI Systems

GFiber•Sunnyvale, CA

18h•$176,800 - $194,500

About The Position

At GFiber, we believe that great internet has the power to drive innovation, strengthen communities, enable the impossible, and do all the everyday things that make all of our world go round. And the job of creating better internet is never done - so we’re growing! Our team is committed to building a place where people who want to make a difference can grow their careers and find their spot to belong. GFiber is an Alphabet company that brings Google Fiber and Google Fiber Webpass internet services to homes and businesses across the United States. Our teams are expanding as we connect more cities and people to exceptional internet. In this role you'll work with the team that is building cutting-edge agentic AI chat assistants that help our customers resolve issues faster and more effectively. This is a hands-on role where you'll own features end-to-end, from design through deployment and production support. This role requires a strong understanding of microservice architecture, RESTful APIs, design patterns, and distributed systems, along with the emerging AI trends and expertise in modern AI systems.

Requirements

Bachelor’s degree in Computer Science, Information technology, a similar engineering discipline, or equivalent practical experience.
5 years of software design and full stack development experience.
Python programming skills with direct production experience.
Practical experience building with LLMs, AI agents, and RAG pipelines, or a demonstrable ability to go deep on new technical frameworks (like MCP) incredibly fast.
Understanding of LLM behavior, limitations and failure modes in production contexts.
Direct experience with GCP (Google Cloud Platform).

Nice To Haves

Experience with the Backend-for-a-Frontend design pattern.
Familiarity with feature flags or configuration management for AI system rollouts.
Familiarity with LLM prompt optimization, prompt patterns, and guardrails against prompt injection/hallucinations.
Understanding of context engineering and how to structure information for LLM consumption.
Experience using AI coding tools like AntiGravity, Claude, Cursor etc
Experience with Java or Kotlin.

Responsibilities

Drive the full lifecycle of agent implementation, from initial design to a live, high-performing production environment using RAG, MCP, and agentic architectures
Test, evaluate, and fine-tune AI agents, RAG pipelines, and Model Context Protocol (MCP) implementations to hit strict performance targets using real-world data.
Implement and optimize REST APIs for seamless system integration
Debug, troubleshoot, and support production systems in real-time
Define and enforce best practices for system design, including scalability, fault tolerance, and performance optimization.
Work closely with frontend developers, DevOps engineers, product managers, and other stakeholders to deliver end-to-end solutions that meet business requirements.
Create and maintain technical documentation for architecture, APIs, and processes to facilitate knowledge sharing and onboarding.
Deploy and manage containerized services on Google Kubernetes Engine (GKE) or Cloud Run.
Implement deep tracking and monitoring for non-deterministic AI agent behaviors using Google Cloud Observability (Stackdriver) or OpenTelemetry.