6 months ago
Responsibilities
- Architect, optimize, and own production ML inference for high throughput, ultra-low latency, and global reliability.
- Extend CUDA, TensorRT, Triton, TVM, and custom GPU kernels to improve inference performance and efficiency.
- Partner with ML, infrastructure, and product teams to deploy, benchmark, and scale production models.
- Optimize cost, cloud spend, carbon footprint, latency, and system efficiency without sacrificing model quality.
- Investigate performance and implement pruning, quantization, distillation, batching, and robust model-serving solutions.
- Set technical strategy and culture for ML inference, while mentoring engineers and collaborating with AI experts.
Requirements
- Hands-on expertise building and optimizing large-scale ML inference systems with measurable performance and cost improvements.
- Deep experience with production model serving, runtime optimization, GPU acceleration, and high-performance deep learning infrastructure.
- Strong software engineering skills in Python, C++, and/or other relevant languages, with systems and distributed-computing expertise.
- Experience architecting or scaling reliable real-time inference systems handling millions of queries per day.
- A track record of cross-functional delivery with ML research or engineering, infrastructure, and product teams.
- Advanced knowledge of model compression, quantization, efficient deployment, and speed-cost-accuracy tradeoffs.
- Preferred qualifications include open-source contributions or technical publications, optimization across NVIDIA, AMD, ARM, and cloud TPUs, inference monitoring and auto-scaling experience, modern MLOps experience, and e-commerce or globally distributed infrastructure experience.
Benefits
- Remote-first work arrangement.
- Candidates should be prepared to interview within one week, with the goal of completing the interview loop within 30 days.
- The interview process includes a live pair-programming session using the candidate’s own IDE.
Categories
About Shopify
Shopify is a leading global commerce company, providing trusted tools to start, grow, market, and manage a retail business of any size. Shopify makes commerce better for everyone with a platform and services that are engineered for reliability, while delivering a better shopping experience for consumers everywhere. Shopify powers millions of businesses in more than 175 countries and is trusted by brands such as Allbirds, Gymshark, PepsiCo, Staples, and many more. Find all our jobs here: www.shopify.com/careers