SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Fractile is building specialized hardware and software systems to accelerate AI inference at scale. Founded in 2022, the company has raised $220M from top-tier investors including Founders Fund and Accel, and is focused on solving the inference speed bottleneck that constrains frontier AI model deployment.
The Software organisation at Fractile develops a comprehensive stack spanning ML compilers, device drivers, systems firmware, runtime environments, ML libraries, developer tooling, and datacenter-scale deployment solutions. The Developer Experience team sits within this organisation and shapes how customers interact with Fractile's inference accelerator.
In this role, you will be part of the Developer Experience team, responsible for identifying, creating, and presenting information on how the Fractile system is being used. You'll provide tooling to help customers optimize their usage while maintaining a shallow learning curve. You'll work across the company to understand the current state of inference hardware development and identify what tools will resonate with LLM engineers, fitting seamlessly into their existing workflows with minimal disruption.
You will be self-driven, capable of identifying tooling opportunities, designing solutions, and delivering them in production-quality form. This role requires deep understanding of how LLM engineers work and what will genuinely improve their productivity. You may have prior experience as a Field Development Engineer (FDE) or at a company providing inference services with proprietary models.
The role is based in Bristol or London and involves working with cutting-edge AI inference hardware and software. You'll collaborate with stakeholders across multiple teams to ensure your tools address real needs and integrate smoothly into existing ecosystems.
**Requirements:**
- Experience with inference frameworks such as JAX and/or PyTorch
- Experience with software development in Python, Rust, C/C++, or similar languages
- Experience monitoring and optimizing code written in CUDA, ROCm, OpenCL, or similar GPU/accelerator frameworks
- Experience monitoring and optimizing LLM deployments with 50+ billion parameters
- Experience working with stakeholders across multiple teams
Note: Certain roles may require additional eligibility checks due to UK, US, and international export control regulations applicable to this technology.
