Backend Engineer, Expansion

Stripe

About The Position

The Web Presence and Platform team at Stripe is looking for a Backend Engineer to join the Expansion pod. This role focuses on building the server-side systems and LLM orchestration layers that power intelligent, dynamic user experiences for customer acquisition. You will design APIs, data pipelines, and inference infrastructure for interactive tools and resources that attract users, with a specific focus on integrating large language models into production-grade services. This is a product-focused role, not a research role, and involves managing prompt pipelines, model routing, guardrails, and output validation.

Requirements

5+ years of backend development experience, with emphasis on building APIs and services that power user-facing experiences.
Experience writing clear, elegant code in a team environment.
Familiarity with LLM APIs and concepts — prompt engineering, token management, embedding models, retrieval-augmented generation, or function calling.
Experience building and operating distributed backend systems — comfortable with service-oriented architectures, async processing, caching layers, and monitoring/alerting in production.
Passion for engineering solutions focused around growth hacking & enablement.
Excellent verbal and written communication.

Nice To Haves

Proven ability to stitch different services and processes together even if you have not worked with them before.
Experience in developing interactive tools and integrating them with existing systems.
Experience building highly complex interactive tools, including state management and data fetching.
Experience with data pipeline orchestration (Airflow, Dagster, Temporal, or similar) and structured output parsing from LLMs.
Experience with prompt versioning, A/B testing model outputs, or building model gateway/routing layers that allow teams to swap or compare providers (e.g., OpenAI, Anthropic, open-source models).
Proficiency with React, with a focus on interactions, animation, performance, and polish.
Experience with A/B testing, synthetic monitoring, or accessibility testing.

Responsibilities

Architect and build server-side systems and LLM orchestration layers for intelligent, dynamic user experiences across acquisition journeys.
Design APIs, data pipelines, and inference infrastructure for interactive tools and resources that attract users.
Collaborate deeply across design, engineering, and cross-functional teams to create new site capabilities.
Integrate large language models into production-grade services that are reliable, performant, and safe.
Manage prompt pipelines, handle model routing and fallback logic, and implement guardrails and output validation.
Develop and implement tooling and platforms to support interactive content tools (e.g., calculators, generators, templates).
Implement feedback mechanisms for continuous improvement of content and product offerings.
Design and build integrations to third-party software and create seamless workflows.
Ensure reliability, security, and responsible AI practices across all LLM-driven features, including content filtering, PII handling, rate limiting, graceful degradation, and output guardrails.
Work with a small team of technically sophisticated engineers who put users first.