Member of Technical Staff, Training Performance Engineer (AI)

TL;DR

Member of Technical Staff, Training Performance Engineer (AI): Optimizing the performance of advanced language models and systems with an accent on improving key model training metrics and ensuring high accelerator utilization. Focus on identifying and removing performance bottlenecks, developing training and profiling tools, and driving innovation in natural language processing.

Location: Hybrid (London, New York, Toronto, Montreal, Paris)

Company

hirify.global is dedicated to scaling intelligence to serve humanity by training and deploying frontier models for AI systems.

What you will do

• Design and write high-performant and scalable software for training.
• Understand architectural modifications and design choices and their effects on training throughput and quality.
• Write low-level CUDA, triton kernels to optimize performance from accelerators.
• Research, implement, and experiment with ideas on supercompute and data infrastructure.
• Collaborate with leading researchers in the field.

Requirements

• Extremely strong software engineering skills.
• Proficiency in Python and related ML frameworks such as JAX, Pytorch, and XLA/MLIR.
• Experience writing kernels for GPUs using CUDA, triton, etc.
• Experience using large-scale distributed training strategies.
• Familiarity with autoregressive sequence models, such as Transformers.

Nice to have

• Publications at top-tier venues (e.g., NeurIPS, ICML, ICLR).

Culture & Benefits

• An open and inclusive culture and work environment.
• Work closely with a team on the cutting edge of AI research.
• Weekly lunch stipend, in-office lunches & snacks.
• Full health and dental benefits, including mental health support.
• 100% Parental Leave top-up for up to 6 months.
• 6 weeks of vacation (30 working days).