How AI is changing software engineering at Shopify with Farhan Thawar

Key takeaways

Engaging with AI tools early gives companies a competitive edge in technology adoption.
Hiring interns is a strategic approach to innovate and cultivate a culture around AI at Shopify.
A hands-on, collaborative mindset in problem-solving fosters a more adaptive company culture.
Leadership roles in tech can benefit from maintaining technical proficiency and engagement.
The presence of AI will likely increase the demand for more software development, leading to greater opportunities for innovation.

Summary

AI Integration at Shopify

Shopify has been ahead of the curve in integrating AI tools, having been one of the first companies outside of GitHub to use GitHub Copilot. Farhan Thawar described how early access to various AI models has helped shape their engineering practices. Shopify promotes a curious problem-solving approach where engineers actively experiment with AI tools across various teams—not limited to just engineering, but also including finance, sales, and support.

The Role of Interns in AI Adoption

Farhan emphasized the value of hiring interns who are 'AI reflexive', meaning they have grown up with technology and AI tools. By bringing in 1,000 interns, Shopify aims to create a culture that embraces AI, encouraging new voices to push the boundaries of what's possible with AI technology.

Shopify's Internal Practices and Tools

Together with Farhan, the episode delves into how Shopify designs its internal tools and processes. They use an internally-built program management tool called 'GSD' to track projects and expect weekly updates from engineers. Furthermore, engineers are encouraged to be hands-on and actively engaged within their technical domains.

AI-Driven Approaches to Leadership and Hiring

Farhan shared insights into Shopify’s leadership philosophy regarding engineering managers and above. All candidates for such positions undergo coding interviews to ensure they remain connected to the technology, reflecting Shopify's culture of blending leadership with technical proficiency.

Reflections and Future Trends

The episode wraps up with thoughts on how the presence of AI is reshaping employment in tech. Farhan expressed optimism that even with AI advancements, the demand for software and innovation will only grow, and leaders should view AI tools as an investment in productivity rather than mere cost.

Show notes

Supported by Our Partners

•⁠ WorkOS — The modern identity platform for B2B SaaS.

•⁠ Statsig ⁠ — ⁠ The unified platform for flags, analytics, experiments, and more.

• Sonar — Code quality and code security for ALL code.

—

What happens when a company goes all in on AI?

At Shopify, engineers are expected to utilize AI tools, and they’ve been doing so for longer than most. Thanks to early access to models from GitHub Copilot, OpenAI, and Anthropic, the company has had a head start in figuring out what works.

In this live episode from LDX3 in London, I spoke with Farhan Thawar, VP of Engineering, about how Shopify is building with AI across the entire stack. We cover the company’s internal LLM proxy, its policy of unlimited token usage, and how interns help push the boundaries of what’s possible.

In this episode, we cover:

• How Shopify works closely with AI labs

• The story behind Shopify’s recent Code Red

• How non-engineering teams are using Cursor for vibecoding

• Tobi Lütke’s viral memo and Shopify’s expectations around AI

• A look inside Shopify’s LLM proxy—used for privacy, token tracking, and more

• Why Shopify places no limit on AI token spending

• Why AI-first isn’t about reducing headcount—and why Shopify is hiring 1,000 interns

• How Shopify’s engineering department operates and what’s changed since adopting AI tooling

• Farhan’s advice for integrating AI into your workflow

• And much more!

—

Timestamps

(00:00) Intro

(02:07) Shopify’s philosophy: “hire smart people and pair with them on problems”

(06:22) How Shopify works with top AI labs

(08:50) The recent Code Red at Shopify

(10:47) How Shopify became early users of GitHub Copilot and their pivot to trying multiple tools

(12:49) The surprising ways non-engineering teams at Shopify are using Cursor

(14:53) Why you have to understand code to submit a PR at Shopify

(16:42) AI tools' impact on SaaS

(19:50) Tobi Lütke’s AI memo

(21:46) Shopify’s LLM proxy and how they protect their privacy

(23:00) How Shopify utilizes MCPs

(26:59) Why AI tools aren’t the place to pinch pennies

(30:02) Farhan’s projects and favorite AI tools

(32:50) Why AI-first isn’t about freezing headcount and the value of hiring interns

(36:20) How Shopify’s engineering department operates, including internal tools

(40:31) Why Shopify added coding interviews for director-level and above hires

(43:40) What has changed since Spotify added AI tooling

(44:40) Farhan’s advice for implementing AI tools

—

The Pragmatic Engineer deepdives relevant for this episode:

• How Shopify built its Live Globe for Black Friday

• Inside Shopify's leveling split

• Real-world engineering challenges: building Cursor

• How Anthropic built Artifacts

—

See the transcript and other references from the episode at ⁠⁠https://newsletter.pragmaticengineer.com/podcast⁠⁠

—

Production and marketing by ⁠⁠⁠⁠⁠⁠⁠⁠https://penname.co/⁠⁠⁠⁠⁠⁠⁠⁠. For inquiries about sponsoring the podcast, email podcast@pragmaticengineer.com.

Get full access to The Pragmatic Engineer at newsletter.pragmaticengineer.com/subscribe