Senior Compiler Engineer – ML Backend for AI Accelerators

Olix; Greater London; On-site; GBP 189,000 - 231,000; Full time

Benefits offered by this job

Equity options

Living-Local bonus

Retirement benefits

Job summary

OLIX is searching for a Senior Compiler Engineer to join the team building the ML backend (compiler, run-time, and debugger) for our next-generation hardware. You will work on seamless support for large AI models and optimize performance in close collaboration with hardware and modelling teams.

The role focuses on designing and implementing a compiler stack for PyTorch, TensorFlow, JAX on custom hardware, with equity and local Living Bonus perks. London office.

Qualifications

• 5+ years of software engineering with a focus on C/C++
• Deep expertise in ML framework internals, compilers, low-level programming and optimisation techniques.
• Deep expertise with TensorFlow, PyTorch or JAX models.
• Experience with LLVM, OpenXLA/XLA, MLIR, TVM.
• Bachelor's degree in CS, EE, maths or related field.
• Personal projects are a differentiating factor.

Responsibilities

• Own and deliver projects on team roadmap that unlock high-impact milestones.
• Architect and build compiler, runtime and debugger for PyTorch, TensorFlow, JAX on custom hardware.
• Optimise performance using layout, fusion, scheduling and tiling to maximise throughput.
• Lead code reviews and uphold best practices in ML backend and performance engineering.
• Stay ahead of GPU and AI accelerator trends and prototype innovations.

Skills

C/C++

ML framework internals

Compiler development

Low-level programming

TensorFlow PyTorch JAX

LLVM OpenXLA MLIR TVM

High-performance computing

Problem solving

Team collaboration

Education

Bachelor's degree in CS/EE/math

Tools

LLVM

OpenXLA/XLA

MLIR

TVM

Job description

OLIX is searching for a Senior Compiler Engineer to join the team building the ML backend (compiler, run-time, and debugger) for our next-generation hardware. You will work on seamless support for large AI models and optimize performance in close collaboration with hardware and modelling teams.

The role focuses on designing and implementing a compiler stack for PyTorch, TensorFlow, JAX on custom hardware, with equity and local Living Bonus perks. London office.