Working Student - LLM Inference Performance (AI)

Location: Munich, Germany

Company

hirify.global is a well-funded AI systems startup developing custom silicon, hardware, and software for high-performance, low-power multimodal generative AI inference for hyperscaler and neocloud data centers.

What you will do

• Learn how hirify.global silicon processes data, manages memory, and synchronizes operations, including how attention, MLP, and Mixture-of-Experts routing map to the architecture.
• Implement, test, and optimize low-level kernels for LLM inference workloads.
• Build analytical and roofline performance models and compare predictions with simulator and real-silicon measurements.
• Develop benchmark harnesses, profiling scripts, and trace visualizations to identify and explain performance bottlenecks.
• Explore AI coding-agent workflows for kernel development, optimization, and benchmarking.
• Collaborate with compiler, runtime, and kernel engineers to turn performance insights into practical improvements.

Requirements

• Currently enrolled in a Master's degree program in Computer Science, Electrical Engineering, Mathematics, or a related technical field.
• Strong programming skills in Python and at least one of C, C++, or Rust.
• Academic or personal-project understanding of computer architecture, memory systems, bandwidth, and parallel computing.
• Interest in low-level programming, hardware performance, and optimization.
• Practical experience using AI coding agents in development workflows, including evaluating and improving their output.
• Experimental mindset with the ability to form hypotheses, analyze measurements, and communicate technical findings clearly.
• Curiosity, initiative, and enthusiasm for learning new technologies.

Nice to have

• GPU or AI accelerator programming experience.
• Embedded systems or bare-metal programming experience.
• Performance profiling, benchmarking, or optimization experience.
• Understanding of LLM inference fundamentals and architectures.

Culture & Benefits

• Hands-on work with real silicon and next-generation AI inference hardware and software.
• Meaningful technical projects supporting engineering teams and future technology generations.
• Collaboration with specialists in hardware architecture, compilers, runtimes, and performance optimization.
• Experience with AI-assisted development and advanced hardware systems.
• People-first culture focused on ethics, integrity, excellence, ownership, collaboration, and inclusion.
• Comprehensive benefits, competitive compensation, flexible spending options, and recognition programs.