Fractile is a UK AI hardware startup building next-generation inference chips and systems for frontier AI.
<div id="message-list_1778230006.062369"> <h1>Modelling Engineer (Mid-Level or Senior)</h1> <p>Fractile · London or Bristol · Full-time · Hybrid </p> <h2>About Fractile</h2> <p>Fractile is building a new class of AI accelerator — designed to run the world's largest language models dramatically faster than existing systems. Founded in 2022 and scaling fast, we work at the intersection of cutting-edge hardware and software, in modern offices in London and Bristol.</p> <p>If you want your work to directly shape the future of AI infrastructure, you'll fit right in.</p> <h2>The Role</h2> <p>To build hardware that doesn't yet exist, you first have to model it — with precision, depth, and an eye for the trade-offs that matter. At Fractile, high-fidelity pre-silicon models shape our architecture, performance, and product design long before hardware exists. This is where you come in.</p> <p>You'll be joining a high-calibre simulation and modelling team that includes engineers with deep expertise in C++, verification, and architectural modelling. This isn't a support function — it's the group that defines how Fractile's hardware behaves.</p> <h2>What You'll Work On</h2> <p>You will develop the pre-silicon models of Fractile's AI acceleration hardware, enabling:</p> <ul> <li>Architectural exploration and definition</li> <li>Functional modelling</li> <li>Performance modelling and bottleneck analysis</li> <li>Early software development on virtual platforms</li> </ul> <p>You'll work closely with hardware, software, and ML teams in a true hardware–software co-design loop. No silos — just tight collaboration across disciplines.</p> <h2>The Team</h2> <p>Fractile's Simulation team is growing and includes:</p> <ul> <li>C++ and SystemC specialists</li> <li>Verification and validation engineers</li> <li>System architects</li> <li>Embedded engineers</li> </ul> <p>You'll be joining a team with real depth — not a lone modelling role.</p> <h2>What We're Looking For</h2> <p>We care about depth of knowledge and a genuine curiosity for the problems we're solving. You may be a strong fit if you have experience in:</p> <ul> <li>Pre-silicon modelling of complex semiconductor IP</li> <li>SystemC or equivalent modelling frameworks</li> <li>C++ for high-performance simulation</li> <li>Performance modelling and architectural analysis</li> <li>Verification and functional modelling</li> </ul> <p>We're especially interested in engineers who can operate across architecture, performance, and functional correctness.</p> <p><strong>Bonus Points</strong></p> <p>These aren't requirements, but they'd make you stand out:</p> <ul> <li>Experience with ML workloads or ML accelerator architectures</li> <li>Prior startup or small-team experience</li> </ul> <h2>Why This Role Matters</h2> <p>The models you build will:</p> <ul> <li>Shape the architecture of Fractile's accelerator</li> <li>Determine performance trade-offs</li> <li>Enable early runtime and compiler development</li> <li>Unblock software teams months before silicon exists</li> <li>Reduce risk across the entire product lifecycle</li> </ul> <p>This is high-leverage engineering — the kind that changes the trajectory of the hardware.</p> <h2>Why Fractile</h2> <ul> <li>Work on genuinely hard problems at the frontier of AI hardware</li> <li>A collaborative, curiosity-driven engineering culture</li> <li>Hybrid working: 3 days onsite, 2 days remote</li> <li>Modern offices in London and Bristol — choose your base</li> <li>Competitive salary and equity</li> </ul> <p><em>Fractile is committed to building a diverse and inclusive team. We welcome applications from people of all backgrounds and actively encourage candidates from underrepresented groups to apply.</em></p> <p> </p> </div> <div id="message-list_unreadDivider"></div>