Senior Deep Learning Tools Engineer – CUDA Tile

This is a fully remote position, open to applicants in California, +2 more states.

📋 Description

• Create and develop performance testing frameworks tailored for deep learning compilers and workloads.

• Establish and manage automated pipelines (CI/CD) to consistently monitor performance across various models, hardware, and compiler modifications.

• Implement benchmarking systems to evaluate latency, throughput, and efficiency of AI and HPC workloads.

• Examine performance trends over time to identify regressions, bottlenecks, and opportunities for optimization.

• Collaborate with compiler and architecture teams to troubleshoot and resolve performance challenges.

• Create tools and dashboards for performance visualization, reporting, and generating insights.

• Facilitate scalable testing across a variety of GPU systems and environments.

• Enhance infrastructure to guarantee reliable, reproducible, and high-quality performance data.

⛳️ Requirements

• Bachelor’s, Master’s, or PhD degree (or equivalent experience) in Computer Science, Computer Engineering, Electrical Engineering, Mathematics, or a related discipline.

• Over 5 years of software engineering experience, with a strong focus on performance engineering, benchmarking, or systems optimization.

• Proficient programming skills in Python (C++ knowledge is an advantage).

• Experience with CI/CD systems and automation frameworks.

• Familiarity with hardware-aware performance analysis, including GPUs, accelerators, or similar systems.

• Experience with deep learning frameworks such as PyTorch, TensorFlow, JAX, or TensorRT.

• Background in data analysis, profiling, and regression tracking.

• Capability to debug intricate system-level problems across both software and hardware layers.

🏝️ Benefits

• Competitive salaries.

• Comprehensive benefits package.

• Equity options.