Staff Engineer, Compiler

What this role involves

This role involves adapting torch.compile to custom hardware, designing kernel DSLs, and developing placement/scheduling passes for distributed memory. The engineer will also work on parallelism-aware lowering, fusion, tiling, and memory planning, with upstream contributions to open-source DSLs like PyTorch, Triton, and Helion.

Skills this posting asks for

• pytorch
• triton
• helion
• compiler
• dsl
• inductor
• ir
• placement
• scheduling
• parallelism
• fusion
• tiling
• memory planning
• isa
• collective primitives
• distributed memory
• tensor parallelism
• pipeline parallelism
• expert parallelism
• sequence parallelism

Requirements

• Level: staff
• Remote policy: onsite

From the employer’s posting

Please Note: To provide the best candidate experience amidst our high application volumes, each candidate is limited to 10 applications across all open jobs within a 6-month period.&nbsp; <span style=…