SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: PLN 260,400 - 352,200 / annual
Graphcore is building the future of AI compute as part of the SoftBank Group. The company develops a complete AI compute stack spanning silicon, software, and datacenter-scale infrastructure.
As a Senior Software Engineer in the ML Software Performance Analysis team, you will own end-to-end performance excellence across Graphcore's proprietary AI hardware and software stack. You'll report to the Performance Analysis Team Lead and collaborate with ML Framework developers, Compiler and Runtime teams, Infrastructure engineers, and Product Management.
Key responsibilities include:
- Own performance analysis across the full ML stack, from model execution to hardware utilization
- Identify bottlenecks and regression trends using profiling, benchmarking, and deep system analysis
- Drive cross-team optimizations involving frameworks, compilers, runtime, and infrastructure
- Design and maintain benchmarking environments for synthetic and large-scale ML workloads
- Produce performance reports translating low-level findings into actionable insights
- Ensure local optimizations improve global system performance
- Partner with engineering teams to guide performance improvements and validate impact
The ML Software Performance Analysis team is part of the wider ML Software Engineering organization, responsible for delivering optimized machine learning solutions. The team focuses on rigorous performance benchmarking, in-depth analysis, and cross-layer optimization from single chip to large-scale distributed systems.
Required qualifications:
- Strong programming skills in Python, C, or C++ with focus on performance-sensitive applications
- Solid understanding of computer architecture, performance profiling, and low-level system behavior (CPU, memory, I/O)
- Experience with benchmarking and analyzing complex, distributed systems
- Familiarity with Linux-based development environments and tools
- Strong problem-solving skills and ability to communicate performance data clearly
- Passion for work and ability to thrive in uncertain, complex environments
Desirable experience:
- Knowledge of ML frameworks, particularly PyTorch
- Performance analysis in GPU-accelerated environments (CUDA, ROCm)
- Hardware performance characteristics in ML context, including high-speed networking (RoCE, RDMA)
- Distributed computing frameworks
