Senior ML Compiler Engineer for AI Accelerator Hardware

Fractile; London Borough of Southwark; On-site; GBP 90,000 - 130,000; Full time

Benefits offered by this job

Equity

Private Medical

Contributory Pension

25 Days holiday

Job summary

Fractile is hiring Senior ML Compiler Engineers to join our team in shaping a full-stack execution engine for frontier AI models. You will help build the compiler stack for our acceleration hardware and push performance for the latest LLMs.

The role offers office-based work in the UK (London/Bristol) with a highly collaborative environment across hardware, runtime, and ML teams. A strong background in compilers, ML, and computer architecture is essential.

Qualifications

• Proven experience of the development of machine learning compilers using MLIR or TVM.
• Up-to-date knowledge of machine learning techniques and technologies.
• Good understanding of computer architecture and performance optimisation techniques.
• Excellent C/C++ skills and experience with industry standard development tools.
• Creative mindset with ownership and drive in a fast-paced environment.
• CS/Engineering degree and 4+ years of industry experience.

Responsibilities

• Develop the machine learning compiler stack for Fractile's AI acceleration hardware.
• Enable industry-leading performance of the latest LLMs on Fractile's accelerators.
• Work with hardware, driver runtime, and ML engineers in a hardware-software co-design methodology.

Skills

ML compiler

MLIR/TVM

C/C++

Perf optimization

Hardware-software co-design

Education

CS/Engineering degree

Tools

GCC/Clang

Job description

Fractile is hiring Senior ML Compiler Engineers to join our team in shaping a full-stack execution engine for frontier AI models. You will help build the compiler stack for our acceleration hardware and push performance for the latest LLMs.

The role offers office-based work in the UK (London/Bristol) with a highly collaborative environment across hardware, runtime, and ML teams. A strong background in compilers, ML, and computer architecture is essential.