AI Kernel Engineer
Indexed description
This is an opportunity to work on cutting-edge accelerator architectures, solving complex performance problems long before hardware reaches production.
You’ll focus on optimising AI workloads across the hardware and software stack, developing low-level kernels and improving the performance of modern machine learning systems.
Working closely with a highly technical team, you’ll analyse AI models, profile workloads, identify bottlenecks and implement optimisations that deliver measurable improvements in throughput, latency and efficiency.
Responsibilities
- Optimise compute-intensive AI workloads across GPUs, AI accelerators and emerging hardware
- Develop and tune low-level kernels for machine learning applications
- Profile, benchmark and analyse system performance using industry-standard tools
- Identify performance bottlenecks across hardware and software layers
- Work with customers and engineering teams to deliver performance improvements
- Contribute to AI benchmarking and performance evaluation initiatives
- Explore new approaches to accelerator programming and AI-assisted optimisation
- Degree in Computer Science, Computer Engineering, Mathematics, Physics or a related technical discipline
- Experience optimising workloads on GPUs, AI accelerators, FPGAs or other high-performance hardware
- Strong understanding of performance analysis, profiling and benchmarking
- Experience with profiling, debugging and performance analysis tools
- Background in inference optimisation or performance-critical AI systems
- Strong C++ and/or Python programming skills
- Excellent communication skills with the ability to work in a collaborative, research-focused environment
Create a free Caio profile to unlock more results and save your role and location preferences.
Unlock free search