Senior Performance Software Engineer – AI & HPC

An innovative semiconductor company at the forefront of next-generation RISC-V architecture is seeking a Senior Performance Software Engineer to join its world-class performance team. This is an opportunity to work on cutting-edge silicon with AI and HPC acceleration, optimizing some of the most demanding applications and benchmarks in the industry.

As a Senior Performance Software Engineer, you’ll play a key role in maximizing the performance of AI, HPC, and other compute-intensive workloads on advanced RISC-V hardware. You’ll collaborate across hardware, compiler and software teams to ensure best-in-class performance for both internal and customer workloads.

Key Responsibilities

• Optimize AI, HPC and benchmark workloads for RISC-V processors with vector extensions.

• Identify and resolve performance bottlenecks using workload characterization and profiling tools.

• Conduct performance analysis across the full system stack — CPU, memory, storage and power.

• Profile and optimize code on pre-silicon environments (simulators, emulators, FPGAs) and production silicon.

• Work closely with customers to tune and optimize their workloads.

• Develop and enhance performance measurement infrastructure and CI/CD integration.

• Collaborate with hardware and software teams to influence co-design decisions.

• Present technical findings internally and at industry events.

Required:

• Bachelor’s or Master’s degree in Computer Science, Electrical Engineering, or related field.

• 3–5+ years of experience in performance engineering or similar roles.

• Strong understanding of computer architecture (CPU, cache, memory hierarchy, buses).

• Hands-on experience with performance profiling and analysis tools (e.g., Linux perf, VTune, flamegraphs, etc.).

• Proficiency in C, C++, or Rust; familiarity with assembly language (any architecture).

• Experience with performance benchmarks such as SPEC CPU, Linpack, Stream, MLPerf, or similar.

• Solid grasp of operating systems, networking and cloud technologies.

• Experience in low-level or bare-metal development.

• Familiarity with version control and CI/CD tools (git, Jira, etc.).

• Strong collaboration and communication abilities.

• Proactive, self-motivated problem solver with a can-do attitude.

• Curious, eager to learn new technologies and cross-disciplinary domains.

Preferred Qualifications

• Experience optimizing ML or HPC workloads.

• Knowledge of Fortran and RISC-V assembly.

• Familiarity with simulators/emulators (QEMU, Gem5, Spike).

• Experience with Docker, Kubernetes, or hypervisors (KVM, Xen).

• Background in open-source software development or contribution.

Why Join?

You’ll be part of a pioneering team shaping the performance landscape of the next generation of AI and HPC processors. This role offers deep technical challenges, opportunities for innovation, and a chance to make a tangible impact in a rapidly evolving industry.