Compiler Engineer

Compiler Engineer - AI Hardware 

Hybrid from Mountain View, CA

Acceler8 Talent is seeking an experienced Compiler Engineer to join a well funded startup whose hardware promises to drastically change the economics of compute for the worlds' largest models.

With >$100m series A in the bank, and a genuinely world-class team with a track record of shipping highly successful products, this company abandons legacy chip design assumptions and strives for the best possible solution for every aspect of their chip - there is no such thing as "good enough".

As a Compiler Engineer, you will play a pivotal role in building the compiler stack that unlocks the full performance of next-generation AI accelerators, working on areas like register allocation, instruction scheduling, loop optimizations and much more. You will work across the entire compiler lifecycle, taking hardware from architectural intent to performant, production-quality software running on real silicon. 

Responsibilities:

• Design and deliver middle and backend compiler infrastructure targeting custom AI accelerators 
• Own and develop lowering pipelines, IR dialects, optimizations, and code generation from high-level representations down to hardware-specific execution
• Build and maintain compiler models and performance tooling to analyze, optimize, and validate architectural and compiler trade-offs
• Collaborate closely with hardware architects, micro-architects, RTL, verification, and system software teams to co-design hardware and compiler features
• Support bring-up and performance debugging on pre-silicon and post-silicon platforms, translating real hardware behavior back into compiler improvements

Qualifications:

• M.S. or Ph.D. in Electrical Engineering, Computer Engineering, Computer Science, or related field with 5+ years of experience in compiler development or related systems software
• Proven experience building LLVM- and/or MLIR-based compilers, including custom passes, dialects, and backend code generation
• Strong proficiency in C++ or Rust, with experience in Python (and willing to learn Rust if you don't know it)
• Excellent knowledge of low-level systems concepts and hardware-software interfaces
• Track record of delivering production compiler technology for ML, AI accelerators, GPUs, CPUs, or other performance-critical systems
• Experience debugging performance and correctness issues across the compiler, runtime, and hardware stack in collaboration with architecture, silicon, and software teams

If you're interested in building the future of AI compute, apply here or reach out to me at ltomaszko@acceler8talent.com to discuss further.