Senior Software Engineer

Key Skills:

Roles & Responsibilities:

• Develop, optimize, and maintain GPU kernels (CUDA, Triton, ROCm) for diffusion, attention, and convolution operators in generative AI models.
• Profile end-to-end inference pipelines (data movement, kernel scheduling, memory transfers) to identify and resolve performance bottlenecks.
• Apply optimization techniques such as operator fusion, tiling, caching, and mixed-precision compute to maximize GPU throughput.
• Collaborate with research teams to productionize experimental layers or model architectures.
• Build benchmarking tools and micro-tests for latency, memory, and throughput regression analysis.
• Integrate kernel improvements into serving stacks, ensuring reliability, repeatable performance, and cost efficiency.
• Work with platform and infrastructure teams to tune runtime configurations and job scheduling for optimal GPU utilization.

Experience Requirement:

• 5 - 8 years of experience in systems or ML engineering, with 2+ years in GPU or accelerator optimization.
• Hands-on expertise with CUDA programming, memory hierarchies, warps, threads, and shared memory.
• Familiarity with profiling tools like Nsight, nvprof, CUPTI for performance analysis.
• Working knowledge of PyTorch, JAX, or TensorFlow internals.
• Proficiency in C++ and Python.
• Experience with mixed precision (FP16/BF16) and quantization.
• Strong analytical skills and a curiosity for system bottlenecks and numerical correctness.

Education: