Sr. Engineer, Kernel Development and Optimization (AI)

TL;DR

Sr. Engineer, Kernel Development and Optimization (AI): Developing performance-critical kernels to unlock hardware capabilities for ML and HPC workloads with an accent on low-level optimization and C++ systems engineering. Focus on designing GPU-style kernels, solving concurrency challenges, and improving throughput via rigorous profiling and benchmarking.

Location: Hybrid based out of Belgrade, Serbia

Company

hirify.global is building next-generation AI compute, specializing in high-performance RISC-V CPUs and revolutionary AI platforms.

What you will do

• Design, implement, and optimize GPU-style kernels, including matrix multiplication and attention primitives.
• Own end-to-end performance, from bottleneck identification to delivering measurable throughput improvements.
• Develop host-side orchestration code and implement parallelization strategies.
• Create micro-benchmarks, regression tests, and tooling to ensure sustained performance gains and correctness.
• Collaborate with compiler, runtime, ML, and hardware teams to integrate kernels into production systems.

Requirements

• Strong C++ systems engineering experience with a focus on performance-critical or low-level software.
• Deep understanding of concurrency, synchronization, latency hiding, and memory trade-offs.
• Data-driven mindset using profiling and benchmarking to guide optimization decisions.
• Ability to debug complex runtime or kernel-level issues in large codebases.
• Location: Must be based in Belgrade, Serbia (Hybrid).
• Eligibility: Must be eligible to access U.S. export-controlled technology (EAR compliance).

Culture & Benefits

• Highly competitive compensation package.
• Work in a culture that values collaboration, curiosity, and solving hard technical problems.
• Opportunity to work with cutting-edge RISC-V CPU architecture and AI hardware.
• Exposure to AI-assisted and agentic workflows for kernel generation and optimization.