About this role

Analyze AI model architectures (including LLMs) and translate them into optimized execution workloads for custom HW/SW platforms
Design and implement high-performance software components for AI frameworks and runtime environments
Optimize AI workloads for: performance (latency / throughput), memory efficiency, parallel execution, numerical accuracy and stability
Identify and remove performance bottlenecks across the stack (model → runtime → hardware)
Contribute to design decisions for AI execution stack and system architecture
Support deployment and scaling of AI workloads in real-world environments

Bachelor’s or Master’s degree in Computer Science, Mathematics, Engineering, or related field
5+ years of hands-on software engineering experience (or AI model development experience)
Strong programming skills in Python and C++
Strong algorithmic thinking and ability to solve complex computational problems
Solid understanding of AI model architectures, especially transformers and LLMs
Experience in performance optimization (compute, memory, and parallelization techniques)
Strong communication skills and ability to work in cross-functional teams

Workloads Engineer

Key skills