
Fractile is building chips to run large language models two orders of magnitude faster. Existing hardware is good for training LLMs, but very poorly suited to subsequent inference of the trained…

Fractile is building chips to run large language models two orders of magnitude faster. Existing hardware is good for training LLMs, but very poorly suited to subsequent inference of the trained…
What they do: Build processors and full-stack systems that fuse memory and compute to accelerate LLM inference
Performance claim: Up to 25x faster inference and ~1/10th the cost (as stated by the company)
Founded: 2022
Notable funding: $220M Series B (May 2026 reported)
Headcount: 83 employees (reported)
AI inference hardware — reducing latency and cost of running large language models.
2022
Computer Hardware Manufacturing
$15M (reported)
Reported seed round following exit from stealth; participating investors reported include Kindred Capital, NATO Innovation Fund, and Oxford Sciences Enterprises
£5M
ARIA Scaling Compute programme grant (reported)
$220M
Reported lead investors named
“Factorial Funds, Accel, Founders Fund, Kindred Capital, NATO Innovation Fund, Oxford Sciences Enterprises, Innovia Capital, Cocoa, and several angel investors (reported)”
| Company |
|---|
Fractile’s mission is to enable a new chapter in the AI revolution. We’re pioneering AI innovation where hardware and software join to create something truly extraordinary, unlocking the power of the world’s largest language models with speed increases of x100. Our team is rapidly expanding, and we're searching for visionary engineers, scientists, and thinkers who share our passion for pushing boundaries and redefining what's possible. If you're ready to join a dynamic group of innovators shaping AI's future, we want to hear from you!
Our ideal candidate could have 0-3 years’ experience, including recent graduates. This is a unique opportunity to accelerate your development, working with an experienced and collaborative team and gaining exposure to a broad range of disciplines. At Fractile, we value ideas from everyone, regardless of title or tenure, and we believe the best engineering happens when people share, question, and learn together. You’ll be joining a culture where your curiosity is encouraged, your input matters, and there’s real room to grow. As a Silicon Verification Engineer, you will be reporting to the Director of Frontend Silicon and will be based in either our Bristol or London office in the UK. We are looking for you to take an active role in building world-class ML/AI IC products for scale-out to data centre applications. We are looking for someone who is passionate about verification – not someone content to go through the motions, but rather looking to push the field further forwards. If you get excited about bringing software concepts to hardware workflows, and enjoy improving established practices to increase tape-out quality and bring down costs, then this is the role for you.
You’ll work closely with colleagues across modelling, system architecture, and RTL design to ensure our RTL releases meet the highest standards of functional quality. That includes contributing to discussions around specification, architecture, and the workflows that connect them. Your work will be integral to delivering our highly disruptive and ambitious product.
We Look For Engineers With The Following Mindset
Required Skills And Experience
Strong software skills
Python preferred, other languages acceptable
Understanding of digital hardware concepts
Ability to read and debug RTL in SystemVerilog
Familiarity with debugging waveforms
Desirable Skills And Experience
Your next opportunity is in here somewhere. Sign up to explore 52,000+ startups and their open roles. No spam. No gamification. Just jobs.
52,000+
Startups
66,000+
Open Roles
1,500+
New This Week
Pre-silicon RTL verification
Verification planning and execution from specification
Building testbenches
Stimulus creation
Functional modelling of hardware blocks
Checker creation
Coverage definition/closure
Transaction-Level Modelling
Whether in UVM, SystemC or another methodology
SystemVerilog Assertions (SVA)
Software fluency in multiple languages
Open source tools for silicon development
Cocotb (used for all our testbench collateral), Verilator, Icarus Verilog
Commercial EDA tools
Formal verification
Working in a monorepo environment alongside software
Bazel is our chosen tool, familiarity is not expected
Contributing to architecture discussions