Tungsten Compiler Engineer for Wafer-Scale AI

Cerebras Systems; Binangonan; On-site; PHP 9,381,000 - 14,384,000; Full time

Job summary

Cerebras Systems is seeking Compiler Engineers to join a small team working on Tungsten, our dataflow language compiler for wafer-scale hardware. You will design and implement compiler passes, contribute to language design, and shape code generation for AI workloads on hundreds of thousands of cores.

Collaborate with ASIC, kernel, and AI teams to align software with hardware, extend the toolchain with runtime and debugger components, and help deliver the fastest AI system in the world.

Qualifications

• PhD in Computer Science or Computer Engineering preferred; exceptional candidates without a graduate degree may apply with strong evidence.
• Substantial experience in compiler development: IR design, optimization passes, code generation, or backend implementation for novel architectures.
• Strong grasp of computer architecture: instruction sets, memory models, dataflow execution, hardware constraints on compilation.
• Systems-level programming ability in C; reason about performance at instruction/memory-access level.
• Ability to view compilation as a design problem; understand interaction between language semantics, IR, and hardware capabilities.
• Excellent communication and interpersonal skills for a small, fast-moving team.

Responsibilities

• Design and implement compiler passes across the Tungsten toolchain: mid-end optimization, backend code generation, instruction scheduling, register allocation, assembler, and linker.
• Co-design language constructs that improve expressiveness and performance for dataflow execution on wafer-scale hardware.
• Develop and iterate on code generation strategies for complex AI workloads, analyzing performance bottlenecks and closing the gap between peak and achieved throughput.
• Extend the compiler to support future hardware architectures as they move from design to silicon.
• Work with ASIC architects and application researchers to inform hardware-software co-design decisions.

Skills

Compiler development

IR design

Backend implementation

C systems programming

Performance optimization

Communication skills

Education

PhD in Computer Science or Computer Engineering

Tools

MLIR

XLA

TVM

Job description

Cerebras Systems is seeking Compiler Engineers to join a small team working on Tungsten, our dataflow language compiler for wafer-scale hardware. You will design and implement compiler passes, contribute to language design, and shape code generation for AI workloads on hundreds of thousands of cores.

Collaborate with ASIC, kernel, and AI teams to align software with hardware, extend the toolchain with runtime and debugger components, and help deliver the fastest AI system in the world.