Senior Compiler Engineer – LLVM, AI Accelerators (Remote)

IC Resources; Greater London; Hybrid; GBP 90,000 - 150,000; Full time

Job summary

IC Resources in London is seeking Senior to Staff-level Compiler Engineers to advance LLVM-based compiler toolchains for high-performance compute platforms. You will focus on performance-critical, hardware-aware compiler work and collaborate closely with architecture and silicon teams.

Ideal candidates bring strong compiler development experience, especially with LLVM, and a background in systems programming and optimising AI accelerator workloads across CPUs, GPUs, and DSPs.

Qualifications

• Development and evolution of LLVM-based and custom compiler toolchains.
• Performance optimisation for AI / ML and accelerator-driven workloads.
• Low-level code generation, backend, and systems-level compiler work.
• Close collaboration with architecture, silicon, and hardware teams to influence real products.
• Strong experience in compiler development (LLVM strongly preferred).

Responsibilities

• Development and evolution of LLVM-based and custom compiler toolchains.
• Performance optimisation for AI / ML and accelerator-driven workloads.
• Low-level code generation, backend, and systems-level compiler work.
• Close collaboration with architecture, silicon, and hardware teams to influence real products.
• Strong experience in compiler development (LLVM strongly preferred).

Skills

LLVM

Compiler development

Systems programming

Performance optimisation

Hardware-aware software

AI accelerators exposure

Tools

LLVM toolchains

Custom compiler toolchains

Job description

IC Resources in London is seeking Senior to Staff-level Compiler Engineers to advance LLVM-based compiler toolchains for high-performance compute platforms. You will focus on performance-critical, hardware-aware compiler work and collaborate closely with architecture and silicon teams.

Ideal candidates bring strong compiler development experience, especially with LLVM, and a background in systems programming and optimising AI accelerator workloads across CPUs, GPUs, and DSPs.