We're building Aide, an AI-native IDE designed for engineers to enjoy problem-solving with agents by their side.

We're currently a team of two, based in London, United Kingdom. Between us, we have been tech leads with experience building testing infrastructure at Meta, payment systems for 150k merchants in India, been an ACM ICPC world finalist and Open-Source contributor to critical infrastructure including gRPC and the Bazel build system. We love dev tooling, and enjoy thinking about the future of programming.

Building a code editor, using the code editor, is one of the most delightful experiences we’ve had as programmers because we get to use the features we build every single day. And lets us design a future that continues to bring us and programmers everywhere the joy of building software, rapidly accelerated with AI.

Our work right now involves coming up with new paradigms for how developers interact with AI code assistants, and vice versa. This requires pushing the state-of-the-art models, of all sizes, to be consistently correct and fast, building the tooling required to connect the editor, code, and models into a seamless user experience, and fine-tune models to work faster and better than the SOTA for the most challenging workflows.

We expect that you:

• Love to ship fast and prototype faster.
• Really, really care about users.
• Can poke around the whole tech stack, from the editor to the model inference layer.
• Build systems that work today, designed to accommodate the rapid model improvements coming our way.
• Think like a philosopher and code like a hacker :)

If any or all of this sounds interesting to you, we work from a beautiful little office in the heart of London, United Kingdom and would love to have you.

As developers, we're currently building the editor we want to use in the AI-native world. We work daily with large language models to build code assistants that can grok large codebases, access the development environment and work alongside the developer (and each other!) in a manner that is seamless, fast, and correct. We architect with data privacy at the centre, and be ready for a future where AI models run natively on developer machines.

Our tech stack is currently divided between:
— The editor: Built on top of VSCode, is an electron app written 100% in TypeScript with very minimal external dependencies. Extensibility and performance are at the heart of the entire codebase, and UI is built imperatively.
— The AI sidecar: Packaged with the editor for every platform and written in Rust, leverages the language's speed and async capabilities for continuous, bidirectional communication with the editor, code on the filesystem and language models.
— We fine-tune custom models for speed, accuracy, and cost critical use-cases, and host them on GPUs on the cloud.