M

Mythic

Power-efficient edge AI processors for inference

Compiler Engineer - Algorithmic Workloads Compilation

Systems Software EngineeringConfirmed live in the last 24 hours
Full-timeHybrid

About the Job

Requirements

  • At least 3 years of professional experience in compilers or high-performance systems software.
  • Proficiency in modern C++ (C++14, C++17, or C++20) and Python.
  • Familiarity with compiler intermediate representations, such as MLIR or LLVM, and their use in representing complex program structures.
  • A solid foundation in program analysis and optimization techniques, such as static single assignment form, loop optimizations, and vectorization.

Responsibilities

  • Extend compiler intermediate representations to represent algorithms not easily captured in deep neural network graphs, including control flow and iterative computation.
  • Develop compilation strategies that unify analog compute with digital subsystems while maintaining performance and correctness.
  • Prototype and optimize algorithms with irregular or dynamic control flow in compiler intermediate representations, applying techniques such as vectorization, predication, and scheduling.
  • Collaborate with hardware engineers to co-design instruction set architecture and features that improve support for algorithmic workloads.
  • Define a roadmap for higher-level programming abstractions that simplify prototyping and accelerate deployment.

Desired Qualifications

  • Hands-on experience developing MLIR or LLVM dialects for control flow, such as scf or cf, or affine/polyhedral representations.
  • Background in compiler-hardware co-design, working with hardware designers to refine instruction set architecture or execution models for efficiency.
  • Proven ability to prototype irregular or control-flow algorithms in compiler intermediate representations and optimize them for performance and resource constraints.
  • Experience extending machine-learning compiler stacks such as ONNX, IREE, XLA, PyTorch, or TVM to support workloads beyond deep neural networks.

About the Company

Mythic

Power-efficient edge AI processors for inference

Mythic designs power-efficient AI hardware for edge deployments. Its main products are the M1076 Analog Matrix Processor, a single-chip accelerator that can run at up to 25 TOPS, and the MP10304 Quad AMP PCIe card, which adds more performance for AI inference on edge devices and servers. The hardware uses analog matrix processing to perform AI computations with low energy usage, enabling high-performance inference in real-world environments without relying on cloud servers. Mythic targets customers that need strong AI performance with tight power budgets, such as tech companies and other businesses with heavy data-processing needs. Compared with typical AI accelerators, Mythic emphasizes analog computation and edge efficiency, offering a compact single-chip solution plus an expansion PCIe card to scale performance. The company's goal is to make high-performance AI inference practical at the edge by delivering power-efficient processors and modules for edge devices and servers.

Company size
51-200
Company stage
Late Stage VC
Total funding
$290.4M
Headquarters
Austin, TX
Founded
2012

Recently Posted Jobs

Explore more opportunities at Mythic

See more jobs