3 days ago
Manchester, United KingdomStaff+
Responsibilities
- Build and optimize the compute platform for AI at scale across Arm Neoverse platforms and cloud-server technologies.
- Analyze and improve end-to-end application and system performance across applications, runtimes, libraries, compilers, assembly, and hardware.
- Debug complex issues, identify performance opportunities, and optimize software for heterogeneous CPU and accelerator systems.
- Work with ML frameworks, LLM inference, agentic AI workloads, distributed AI systems, scheduling, batching, KV-cache management, and collective communications.
- Deliver sophisticated technical work involving multiple contributors and collaborate with Arm teams, open-source communities, and partners.
- Mentor and support colleagues through coaching, career development, wellbeing support, or performance review activities.
Requirements
- Excellent software engineering and programming skills, preferably in C++ and Python.
- Familiarity with Linux development environments, profiling, debugging, and performance analysis.
- Interest in end-to-end application and system performance from high-level applications through underlying hardware.
- Experience taking responsibility for sophisticated technical work involving multiple contributors.
- A degree in a computational or numerate subject, or equivalent experience.
- Experience with ML frameworks and LLM inference such as PyTorch, vLLM, SGLang, or llama.cpp is desirable.
- Experience optimizing CPU performance in heterogeneous CPU and accelerator systems is desirable.
- Familiarity with agentic AI frameworks and protocols, databases, vector search, retrieval systems, containers, and cloud/server infrastructure is desirable.
- Understanding of batching, scheduling, KV-cache management, collective communications, distributed AI workloads, and parallel programming is desirable.
- Experience optimizing software for AArch64/Arm servers, including Neon, SVE, and SME, is desirable.
- Open-source contributions and experience working across low-level and high-level software abstractions are desirable.
- Strong communication skills and the ability to work independently, make pragmatic decisions, and navigate ambiguity and change.
Benefits
- Attractive reward package with generous stock awards.
- Progressive leave policy including generous parental leave, days of care, and four weeks of sabbatical every four years.
- Flexible working hours and hybrid working, with team-specific hybrid patterns.
- Open and inclusive working environment supporting psychological safety, innovation, and professional growth.
- The role is based in Arm’s Manchester office.
About Arm
Arm’s foundational technology is defining the future of computing. A future built by the greatest technology ecosystem in the world. A future built on Arm. Arm is everywhere technology matters. Technology matters everywhere. Together, we’ll power every technology revolution moving forward, including cloud computing, automotive and autonomous systems, IoT, the metaverse, and beyond. Changing the world. Again. On Arm.