Normal Computing
Normal Computing
51 – 200 Employees
The available profile information identifies Normal Computing as a company founded in 2022, but does not describe its products, services, industry, or hiring context. More company-specific details are needed to provide a useful overview for job seekers.

Compiler Backend Engineer for Custom AI Hardware

Develop code generation, scheduling, and memory planning for Normal Computing’s custom AI hardware. Optimize LLM inference across simulators, FPGA prototypes, and future silicon.

Description

  • Develop compiler passes that translate lowered programs into code for custom hardware
  • Create compilation methods for problems conventional techniques cannot handle
  • Schedule and place computation and data across hardware resources
  • Lead fusion and dispatch decisions for LLM inference
  • Work at the boundary between compiler software and hardware
  • Share compiler constraints with hardware architects during pre-silicon design
  • Test optimizations with simulators, FPGA prototypes, and eventually silicon
  • Maintain a reliable performance regression suite
  • Choose which operations in frontend-lowered programs use generated code or hand-tuned kernels

Requirements

  • Substantial experience optimizing compilers or generating code for accelerators or other non-CPU targets, including scheduling, tiling, fusion, or resource allocation
  • Ability to work close to hardware, including reasoning about memory bandwidth and utilization
  • Readiness to develop compilation methods from first principles
  • A record of delivering optimizations that improved measured performance
  • Experience building software for changing hardware, from simulation through bring-up
  • Fluency in Python
  • Familiarity with C, C++, or Rust
  • Experience with PyTorch’s compilation stack or other machine learning compilers is a plus
  • Experience compiling for in-memory, spatial, or other non-von-Neumann computing targets is a plus
  • Background in logic synthesis or place-and-route is a plus
  • Experience with cycle-level or performance simulators is a plus
  • Open-source contributions to compiler or kernel infrastructure are a plus
  • Published or presented work on compilers or performance is a plus

Benefits

  • Equity
  • Performance-based incentives
  • Comprehensive compensation package
  • Benefits intended to support employee well-being and professional development

Related Jobs

Commure

Senior Software Engineer, Claims Intelligence

Commure

Build Commure’s AI-powered healthcare claims infrastructure, including clearinghouse integrations and EDI pipelines. Develop eligibility routing and scalable revenue cycle rules.

Open