Engineering Manager – Compiler & Performance Modelling

Job Specification:

Role overview:

Lead and scale the Compiler & Performance Modelling teams responsible for enabling the performance of high-performance AI accelerator platforms. Own the technical strategy, drive execution, and build a high-performing, ambitious engineering organisation. Ensure that compiler and performance modelling activities deliver world-class results that align with broader product and hardware objectives. Provide senior technical leadership, mentor emerging leaders, and establish scalable processes across hardware, software, and performance engineering domains.

Key responsibilities:

• Lead and grow high-performing compiler and performance modelling teams in a fast-paced, high-expectation environment

• Own delivery of complex, cross-functional projects spanning hardware, software, and performance engineering that drive business and customer outcomes

• Define the future performance of AI accelerator platforms through functional, roofline, and performance modelling

• Shape engineering strategy and architecture, aligning hardware and compiler performance with product roadmap and technical vision

• Build organisational capacity by hiring exceptional engineers, mentoring emerging leaders, and establishing scalable processes

• Drive quality and reliability across pre-silicon emulation, compilation, and distributed AI inference

• Partner cross-functionally with hardware, software, and systems teams to bring AI accelerator platforms to market

Required skills & experience:

• 5+ years managing engineering teams of 5–10 in a high-performance, fast-paced environment; experience in hyper-scaling and managing managers preferred

• Proven expertise in ML or NPU compiler development and performance modelling; hands-on experience with LLVM, MLIR, XLA/OpenXLA, SystemC, Gem5, or QEMU

• Strong track record of leading world-class teams and delivering measurable business and customer outcomes

• Thrive in ambiguity, with the ability to adapt quickly to rapidly changing conditions

• Experience in hiring competitive candidates and crafting a compelling vision for the team

• Coaching mindset with ability to guide engineers to reach their peak potential

Desirable experience:

• Experience with high-performance AI hardware platforms

• Exposure to distributed AI inference systems and end-to-end hardware/software integration

Tools & methods:

• Compiler and performance modelling toolchains (LLVM, MLIR, XLA/OpenXLA, SystemC, Gem5, QEMU)

• Pre-silicon emulation and testing

• Performance analysis frameworks and metrics

• Cross-functional project management and execution methodologies

What success looks like:

• Teams deliver world-class compiler and performance modelling results aligned with product objectives

• Clear technical strategy and execution that drives AI accelerator performance

• High-performing, scalable engineering organisation with strong leadership and mentorship

• Successful delivery of cross-functional projects across hardware, software, and systems

• Positive impact on business outcomes and customer adoption

Location: London (Fully Remote)

Salary: £208,000+ + stock options benefits

Please contact us for further details.