Sourcegraph logo

Software Engineer - Cody Strategy

Sourcegraph (tech)

Location Type:

About Sourcegraph

Who we are

Our mission at Sourcegraph is to make it so that everyone can code, not just ~0.1% of the population. Our code graph powers Cody, the most powerful and accurate AI coding assistant, as well as our Code Search product, which helps devs explore their entire codebase and make large-scale migrations and security fixes. We’re building software that builds software, and in doing so we’re making devs more productive and preparing for a world where a lot more code gets written.

It’s an exciting time to join Sourcegraph. AI has taken over the world, and we’ve spent the last 10 years building infrastructure that’s integral to making AI generated code more powerful and accurate. Our customers include 4/5 FAANG companies, 4 of the top 10 banks, government organizations, Uber, Plaid, and many other companies building the software that pushes the world forward. We’ve raised $225M at a $2.625B valuation from Andreessen HorowitzSequoiaRedpointCraft and others. We’re making ambitious bets on our future and we’re looking to hire exceptional people to join our team as we make Sourcegraph one of the biggest and most influential companies in the world.

Why this job is exciting

Cody is an AI coding assistant that lives in your editor that can find, explain, and write code. Cody uses LLMs and the Sourcegraph search engine and code graph, providing answers that eliminate toil and keep human programmers in flow. You can think of Cody as your programmer buddy who has read through all the code on GitHub, all the questions on StackOverflow, and all your organization’s private code, and is always there to answer questions you might have or suggest ways of doing something based on prior knowledge.

The Cody Strategic team is aimed at turning the largest, most world-recognizable brands into Cody Champions. We do this by partnering with a small number of highly engaged strategic customers to build product functionality that enables these customers to successfully deploy the most-loved coding assistant, but at massive scale. You will work closely with the ML Infrastructure team, all the Cody teams across Cody’s e2e service stack, and teams across Sourcegraph to bring the best-of-class coding assistant to your favorite big brands. The Strat team focuses on one or two projects at a time, delivers and scales them, and then works to hand them off to the other Cody teams so that it just becomes part of how Cody is operated. This is high-impact work and has the attention of the entire company. You will be supported by Eng, Design, Product, Legal and the go-to-market teams, and you are joining a team of very talented and experienced engineers who have already accomplished amazing things in a short time. They will be there to help you hit the ground running and guide your work.

Job Requirements

About you

You are a full-stack software engineer with at least 2 years of industry experience, equally comfortable with frontend and backend work as needed, with the ability to pick up frameworks quickly and deliver high-quality work. Ideally, you have worked directly with enterprise customers as a SaaS developer. Or perhaps you have worked with internal customers on large cross-functional projects. You should enjoy cross-functional, cross-company collaboration, since that is the bread and butter of the Cody Strat team.

Our Strat customers are typically deployed with complex legacy configurations, and we often need to build bridges into those systems. Much of the Strat work is becoming ML-oriented in nature, as our investment in Cody AI increases and our Strat customers become early adopters. LLMs and their ecosystem are at the core of Cody’s architecture, so you ideally have prior experience working with LLM-based applications, and should be seeking to increase your knowledge of AI/ML as the space quickly evolves.


  • Comfortable with developing and deploying software and services on at least one major Cloud provider, with preference for experience with GCP, as most of your Cloud work will be on GCP.
  • Comfortable with at least the basics of Docker, Kubernetes, Linux, and systems programming
  • Experience with Go (minimum) and in an ideal world, TypeScript, Java, and various scripting languages
  • You have used Cody and understand Cody’s current architecture, and you have your own opinions about the directions it could and should go next.

Nice-to-haves: (All optional, but each would enable you to have even higher impact.)

  • Postgres. If you have very deep Postgres experience, you may be in luck.
  • Node.js. Cody’s cross-client logic is largely in Node.js, and being able to contribute there is helpful.
  • Understanding of the modern LLM ecosystem especially as it pertains to coding and AI assistants, including the basics of prompt engineering and retrieval-augmented generation (RAG) applications.
  • Understanding of compiler construction, and experience working with tools that work with code. We have a code graph that is central to Cody’s operation, and you may be working with it at scale.
  • Frontend programming with React. If you have this specialty, it’s often in demand on this team, e.g. for delivering new administrative workflows and user onboarding experiences.
  • Rust. More and more of our code is being written in Rust, and you may need to fiddle with it at some point.
  • Kotlin and Java Swing, since one of our flagship Cody clients is IntelliJ, and it is often in need of Enterprise-specific features to help close large deals.
  • Plugin development with Neovim or Emacs. Our Strat customers come in all shapes and sizes.