Fractile - Developer Experience / DevEx

• Fractile was founded in 2022 on the bet that, eventually, the world’s most capable AI systems would be limited in their impact by the time taken to produce useful outputs. We bet everything on the logical conclusion: that the only way to truly unlock this latent value, to make speed viable at scale, was to radically re-invent the hardware that we run our frontier AI models on. Ever since, we have been building chips and systems that tackle this problem: how to efficiently generate output at thousands of tokens per second, while handling the complexity and capacity challenges of operating large models at very long contexts. • The workloads that push to the limits of the current frontier are already transformational; it is the technical and economic limits on inference speed that are constraining progress. The defining work of the 21st century will be marked by the engine of inference delivering immense and diffuse chains of intellectual inquiry, in drug discovery, in software engineering, in materials discovery, in any field where progress is driven by deep reasoning and intelligence to resolve complex problems. • Developer Experience sits within the Software organisation at Fractile, which is responsible for developing a full software stack for our groundbreaking AI inference systems. That's everything from ML compilers, device drivers and systems firmware, application level runtime and ecosystem integrations, ML and compute libraries, great developer tooling and a full portfolio of simulators, through to datacenter scale workload deployment solutions. At Fractile, we know that a fantastic software stack is a critical and central part of any AI inference solution and it sits at the heart of everything we're doing. • The Developer Experience team at Fractile helps shape how our customers interact with the Fractile inference accelerator. We work across the company to identify, create, and present information on how the system is being used, as well as providing the tooling to help optimise our customers' usage of the system, while keeping a shallow learning curve. • As a member of the Developer Experience team you will need to understand the current state of development for inference hardware. You will need to be able to identify what will work well for engineers wanting to identify potential opportunities for performance improvements, while knowing what tooling will fit into an existing LLM engineer's workflow with the minimal amount of disruption and effort. • We're looking for someone who is self-driven and capable of identifying tooling opportunities, designing those tools, and delivering them in a way which will fit in with an LLM engineer's existing toolset. You will have worked in this area before, possibly as an FDE or at a company that provides inference services using their own models, and have the ability to develop new tools that are designed to be functional and easy to learn and use. • Experience with inference frameworks such as JAX and/or PyTorch • Experience of software development in Python, Rust, C/C++, or a similar language • Experience monitoring and optimising code written in CUDA, ROCm, OpenCL, or similar • Experience monitoring and optimising LLM deployments with 50+ billion parameters • Experience working with stakeholders across multiple teams