AI KERNEL OPTIMIZATION ENGINEER

What you'll be doing:

As an AI Kernel Optimization Engineer, you will play a key role in optimizing high-performance compute kernels to push the limits of AI Inference on RISC-V platforms.

You will design, implement, and optimize AI compute kernels (Gen AI Large Language Model, AI Vision, CNNs, etc) and runtime components to fully exploit the underlying hardware architecture - from vector/matrix units and memory hierarchies down to the assembly level.

Your work will directly influence how efficiently AI models run on SoCs, shaping the performance of next-generation inference accelerators. You will collaborate closely with hardware architects, compiler engineers, and AI framework developers to achieve optimal hardware–software co-design.

Your main responsibilities will include leading and contributing to:

· Develop, optimize, profile, and debug AI compute-intensive kernels (e.g., GEMM, attention, activations) targeting RISC-V architectures.

· Identify and resolve performance bottlenecks at the ISA, compiler, and runtime levels.

· Collaborate with hardware and architecture teams to influence design decisions and improve real-world AI performance.

· Contribute to the development and optimization of AI runtime and graph execution engines.

· Evaluate, benchmark, and optimize AI inference workloads on platforms.

· Develop performance analysis tools and automation scripts for profiling, validation, and performance optimization.

· Work with AI frameworks (e.g., vLLM, SGLang, PyTorch, TensorRT-LLM) to ensure efficient mapping to targets.

· Stay up to date with AI kernel optimization trends, emerging hardware acceleration techniques, and open-source developments.

· Share technical expertise and contribute to knowledge sharing and continuous improvement within the team.

What we're looking for:

Technical skills:

· Strong background in low-level performance optimization (vectorization, memory access optimization, loop unrolling, instruction scheduling, data-tiling, etc.).

· Proficiency in C/C and good understanding of assembly-level optimizations (SIMD, intrinsics, compiler flags).

· Solid understanding of CPU/GPU/AI accelerator architecture (pipelines, caches, memory hierarchies, compute units).

· Experience with profiling and performance analysis tools (perf, VTune, nvprof, etc.).

· Strong knowledge of parallel programming (SIMD, multithreading, OpenMP, CUDA, or similar).

· Solid software engineering skills (version control, CI/CD, testing).

· Experience with RISC-V architectures or other custom ISAs is a plus.

Nice to have

· Experience with AI inference workloads or libraries (e.g., BLAS, cuDNN, oneDNN, TVM, or similar).

· Familiarity with MLIR/LLVM or other compiler infrastructures.

· Contributions to open-source AI inference engines or kernel libraries.

· Understanding of NUMA architectures or heterogeneous computing.

· Experience with quantization and mixed precision inference.

Profile:

· MSc or PhD in Computer Engineering or Computer Science, or equivalent practical experience.

· 3 years of experience in performance optimization for AI Inference (or HPC use cases).

· Passion for performance and detail-oriented mindset.

· Strong analytical and problem-solving abilities.

· Leadership, collaborative, and open to cross-disciplinary work.

· Comfortable working in an international, fast-evolving startup environment.

Of course, you might not have all of those required skills But feel free to apply anyway and explain to us why you believe you are the right person for the job.

Contract Information:

· Type of contract: Permanent contract

· Starting date: As soon as possible

· Location: Montbonnot (38)

What we can offer you:

· Competitive salary & performance-based RSU (free shares)

· Hybrid work model

· Additional paid leave (RTT)

· Meal vouchers (Edenred)

· Premium health coverage (Malakoff Humanis)

· Sustainable mobility incentives

· Generous paternity leave

· Monthly team activities (laser game, hiking, sailing, karaoke…) and large-scale company events

About the recruitment process:

· First interview with the line manager

· Second interview with the team

· Final interview with HRD or CEO

Equal Opportunity Statement:

KALRAY is committed to creating a diverse and inclusive environment,