Staff Technical Lead (AI)

TL;DR

Staff Technical Lead (AI): Building and optimizing high-performance inference systems for large-scale generative models with an accent on kernel authoring, model parallelism, and compiler strategies. Focus on leading a team of engineers to achieve industry-leading performance benchmarks and scaling generative media infrastructure.

Location: San Francisco (Onsite)

Company

hirify.global is a high-growth startup building next-generation infrastructure for generative media, focused on pushing the limits of model inference performance.

What you will do

• Set technical direction for inference systems including kernels, ML compilers, and distributed serving.
• Lead hands-on technical initiatives by contributing directly to performance critical code and optimization bottlenecks.
• Collaborate with research and applied ML teams to bridge the gap between model development and efficient production deployment.
• Implement advanced strategies such as quantization, kernel optimization, and model parallelism.
• Mentor engineers and scale the technical performance team through strategic coaching and high-impact project management.

Requirements

• Deep expertise in ML performance optimization and inference for large-scale generative models.
• Proven command of the full performance stack including PyTorch, TensorRT, TransformerEngine, Triton, and CUTLASS kernels.
• Expertise in advanced techniques: quantization, kernel authoring, compilation, and distributed serving.
• Leadership experience in scaling high-performing technical teams.
• Ability to collaborate cross-functionally with researchers and applied ML engineers.

Culture & Benefits

• High-impact role at a fast-growing, well-funded startup scaling generative AI infrastructure.
• Opportunity to work on industry-leading performance challenges with real-world impact for creative solutions.
• Collaborative environment that values both individual technical excellence and strategic team leadership.