Ricursive Intelligence

Staff Compiler Engineer, CPU & ML Accelerators

Ricursive Intelligence
Apply
2 days ago
Palo Alto, CA, USAStaff+

Responsibilities

  • Own the compiler backend for CPU and accelerator cores, including instruction selection, scheduling, register allocation, and target-specific optimization.
  • Add standard and custom vector, matrix, bit-manipulation, and domain-specific instruction extensions across the compiler, assembler, linker, intrinsics, and binutils.
  • Build ML compilation flows from PyTorch and JAX through MLIR to hardware, including dialects, tiling, data layout, vectorization, and kernel generation.
  • Lead hardware/software co-design by evaluating ISA and microarchitecture features against simulators and performance models and reporting quantitative results.
  • Own benchmark suites, differential testing, fuzzing, and CI across simulators, FPGA, and silicon.
  • Apply learned cost models, autotuning, and ML-guided optimization heuristics to compiler development.
  • Set the technical roadmap, mentor engineers, and upstream contributions to open-source projects.

Requirements

  • BS in Computer Science, Computer Engineering, Electrical Engineering, or a closely related technical field.
  • 8+ years of compiler development experience, including substantial hands-on backend and code-generation work for a CPU or accelerator target.
  • Expert C++ skills and deep knowledge of LLVM or GCC internals.
  • Track record of shipping a production compiler toolchain for real hardware, including target bring-up, ISA extension support, or optimization work in a shipped compiler.
  • Experience leading multi-quarter technical efforts across several engineers or teams.
  • Preferred: MS or PhD focused on compilers, programming languages, or computer architecture.
  • Preferred: experience with vector or SIMD ISAs, ML accelerators, DSPs, open-standard ISA ecosystems, MLIR, XLA, TVM, Triton, IREE, torch.compile, kernel performance tuning, ML applied to compilers, ML systems, architecture simulators, or performance modeling.
  • Preferred: publications at PLDI, CGO, CC, ASPLOS, MICRO, ISCA, or MLSys, and upstream contributions or code ownership in LLVM, MLIR, GCC, or binutils.

Tech Stack

Categories

Ricursive Intelligence

About Ricursive Intelligence

11-50 employees

Ricursive Intelligence builds AI systems that co-optimize machine learning models and the chips that run them, starting with AI-driven chip design tools for semiconductor and AI hardware teams. Its business focuses on software and research that closes the loop between model performance and silicon layout to accelerate development cycles. Privately held and founded in 2025, it operates at the intersection of AI infrastructure and semiconductor design.

Contact me