Remote Staff Principal GPU Engineer — Elite Kernels

Aurtiro; United States; Remote; USD 250,000 - 320,000; Full time

Benefits offered by this job

Equity

Annual performance bonus

Job summary

Aurtiro, a leading financial compute platform, seeks a senior hardware systems and compiler engineer to own compute kernels and low-level compilation passes for AI inference engines.

You will work at the intersection of Triton, CUDA C++, PTX/SASS assembly, and ML compiler frameworks, optimizing memory paths and instruction-level parallelism for real-time workloads. Remote/hybrid options apply in the U.S. or Canada.

Qualifications

• 6-15+ years of low-level systems, compiler architecture, or GPU infrastructure engineering experience.
• Custom Kernel Mastery: Proven track record of writing, optimizing, and deploying custom Triton and CUDA C++ kernels in production.
• Low-Level Compiler Architectures: Direct experience with ML compilers and IR frameworks (TorchInductor, Triton IR, TVM, XLA, MLIR, or PTX/SASS analysis).
• Hardware Execution Telemetry: Deep expertise using NVIDIA Nsight Compute (NCU) and Nsight Systems (Nsys) to profile stalls, pressure, and pipelines.
• Hardware Execution Optimization: Knowledge of GPU microarchitecture, Tensor Cores, memory bandwidth, Roofline, and fused operators.

Responsibilities

• Author, fuse, and optimize low-level Triton and CUDA kernels for high-throughput model execution paths.
• Build and extend low-level compiler passes to optimize compute primitives for dynamic shapes and token routing scenarios.
• Conduct rigorous hardware execution analysis (TFLOPs, cache utilization, warp execution) to push kernels toward hardware limits.

Skills

Low-level systems

Compiler architecture

GPU infrastructure

Tools

NVIDIA Nsight Compute

NVIDIA Nsight Systems

Triton

TVM

MLIR

PTX/SASS analysis

Job description

Aurtiro, a leading financial compute platform, seeks a senior hardware systems and compiler engineer to own compute kernels and low-level compilation passes for AI inference engines.

You will work at the intersection of Triton, CUDA C++, PTX/SASS assembly, and ML compiler frameworks, optimizing memory paths and instruction-level parallelism for real-time workloads. Remote/hybrid options apply in the U.S. or Canada.