Backend Compiler Engineer (AI)

Location: United States; listed areas include Mountain View, Palo Alto, Santa Barbara, Greater Boston, Boston, the San Francisco Bay Area, Berkeley, and California.

Salary: $180,000–$250,000 annually.

Company

hirify.global is partnering with an AI hardware startup developing a specialized accelerator and its software stack.

What you will do

• Design and deliver compiler backend components, including IR transformations, lowering, and code generation.
• Map graph and model computation to the capabilities and constraints of a specialized processor.
• Make compiler decisions involving memory behavior, scheduling, data movement, dependencies, and hardware execution.
• Debug correctness and performance issues across compiler, runtime, and hardware interfaces.
• Evaluate compiler changes with real workloads and device execution; build tests to detect miscompilations and regressions.
• Collaborate with architecture, kernel, runtime, model, and accelerator-stack teams as the platform evolves.

Requirements

• Production ownership of compiler backends, lowering, IR, transformation passes, or code generation.
• Strong compiler fundamentals, graph reasoning, and C++ software engineering.
• Understanding of intermediate representations, transformation legality, dependencies, and the relationship between graph structure and execution.
• Ability to explain and implement backend design decisions and their effects on memory use, scheduling, correctness, and device performance.
• Ability to independently deliver substantial compiler components and debug complex technical problems.
• Experience using tests, debugging, and workload results to validate compiler changes beyond API integration or routine maintenance.

Nice to have

• Compiler work targeting accelerators, GPUs, NPUs, DSPs, or other specialized processors.
• LLVM or MLIR experience involving substantive compiler design and implementation ownership.
• Experience debugging compiler behavior against runtime or real device execution, including memory, scheduling, and performance analysis.
• Approximately five years of relevant experience when supported by deep production ownership and independent technical judgment.

Culture & Benefits

• Work across the accelerator stack with architecture, runtime, kernel, and model teams.
• Contribute as the architecture and software platform evolve.