Full Stack Engineer, Expansion

at Stripe

📍 Toronto, Canada

CAD 172,000-258,000 per year

MIDDLE

✅ On-site

Tech Stack
Tag name is followed by "@" symbol and proficiency level value. About proficiency levels:

1-2 — basic awareness. Minimal hands-on experience, and a rudimentary understanding of the technology's purpose;

3-6 — daily use. Comfortable and regular usage, capable of handling common tasks and challenges related to the technology;

7-9 — you are an expert, you can teach others, you know all the pitfalls and tricks;

10 — exceptional knowledge, comprehensive understanding, and adeptness in all aspects of the technology, including advanced problem-solving. Think twice before claiming or demanding such level.

A/B Testing @ 3 AI API @ 3 Airflow @ 3 Communication @ 3 Dagster @ 3 Data Pipelines @ 3 LLM @ 3 Machine Learning Prompt Engineering @ 2 RAG React @ 5 Security

Details

Stripe is a financial infrastructure platform for businesses. The Web Presence and Platform team builds Stripe's public websites and the internal systems that make them fast, stable, and easy to update.

This role is focused on the systems behind web experiences, including APIs, data pipelines, model orchestration, and service reliability for LLM-driven user experiences. The Expansion pod works on user journeys, interactive tools, and targeted experiences for global users.

As a full stack engineer, you will architect and build server-side systems and LLM orchestration layers for intelligent, dynamic acquisition experiences. You will design APIs, data pipelines, and inference infrastructure for interactive tools and resources, while integrating large language models into reliable, performant, and safe production services. This is not a research or machine learning training role; the focus is on integrating LLMs into user-facing products through prompt pipelines, model routing and fallback logic, guardrails, and output validation.

Responsibilities

Develop tooling and platforms for interactive content tools such as calculators, generators, and templates.
Implement feedback mechanisms to continuously improve content and product offerings.
Design and build integrations with third-party software and create seamless workflows across tools.
Ensure reliability, security, and responsible AI practices across LLM-driven features, including content filtering, PII handling, rate limiting, graceful degradation, and output guardrails.
Collaborate with a small team of technically sophisticated, user-focused engineers.

Requirements

Minimum Requirements

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

Preferred Qualifications

Ability to connect different services and processes, including unfamiliar ones.
Experience developing interactive tools and integrating them with existing systems.
Experience building complex interactive tools, including state management and data fetching.
Experience with data pipeline orchestration tools such as Airflow, Dagster, Temporal, or similar, as well as structured output parsing from LLMs.
Experience with prompt versioning, A/B testing model outputs, or building model gateway and routing layers for comparing or switching between providers such as OpenAI, Anthropic, and open-source models.
Proficiency with React, particularly interactions, animation, performance, and polish.
Experience with A/B testing, synthetic monitoring, or accessibility testing.