Senior Deep Learning Tools Engineer – CUDA Tile
Core
Designing performance testing frameworks, automated pipelines, and benchmarking systems for deep learning compilers to ensure measurable, scalable performance improvements across AI workloads.
Role type
Senior IC deep learning tools engineer (performance validation & infrastructure)
Builds
Automated performance testing frameworks, CI/CD pipelines, benchmarking systems, and visualization dashboards for deep learning compilers
Domain
Deep learning compilers, GPU systems, high-performance computing (HPC)
Deliverable
production ML models | infrastructure
Required skills
Python, C++, CI/CD systems, hardware-aware performance analysis, deep learning frameworks (PyTorch, TensorFlow, JAX, TensorRT), data analysis, profiling, regression tracking, system-level debugging
Preferred skills
GPU performance optimization, compiler internals (LLVM, MLIR, CUDA), large-scale telemetry systems, hardware/software co-design, distributed testing infrastructure
Technologies
Python, C++, PyTorch, TensorFlow, JAX, TensorRT, LLVM, MLIR, CUDA
Responsibilities
Design performance testing frameworks for deep learning compilers; Build and maintain automated CI/CD pipelines for performance tracking; Implement benchmarking systems for latency, throughput, and efficiency; Analyze performance trends to identify regressions and bottlenecks; Partner with teams to debug performance issues; Develop tools and dashboards for performance visualization; Enable scalable testing across diverse GPU systems; Improve infrastructure for reliable performance data
Seniority
Senior, hands-on IC