Senior ML Compiler Engineer for High-Speed AI Accelerators

Fractile; Greater London; On-site; GBP 90,000 - 140,000; Full time

Benefits offered by this job

Equity

Private medical

Dental

Vision

Pension

25 days holiday

Job summary

Fractile is seeking a Senior ML Compiler Engineer to help build the compiler stack for our AI acceleration hardware. You will work in a collaborative environment with hardware, driver runtime, and ML teams to push performance on the latest LLM workloads.

You can base yourself in London or Bristol, contributing to a groundbreaking system that aims to dramatically reduce inference time and enable scalable AI at scale. A dynamic startup culture supports ownership and rapid iteration.

Qualifications

• 4+ years of industry experience in ML/编译器 development or related field.
• Proven experience developing ML/AI compilers using MLIR or TVM.
• Strong C/C++ software development skills and familiarity with toolchains.
• Solid understanding of computer architecture and optimisation techniques.

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.
• Collaborate with hardware, runtime, and ML engineers in a hardware-software co-design workflow.

Skills

C/C++

MLIR/TVM

Computer architecture

Performance optimisation

Education

CS/Engineering/Math/Physics degree

Tools

MLIR

TVM

Job description

Fractile is seeking a Senior ML Compiler Engineer to help build the compiler stack for our AI acceleration hardware. You will work in a collaborative environment with hardware, driver runtime, and ML teams to push performance on the latest LLM workloads.

You can base yourself in London or Bristol, contributing to a groundbreaking system that aims to dramatically reduce inference time and enable scalable AI at scale. A dynamic startup culture supports ownership and rapid iteration.