E

ElastixAI

Software platform optimizing AI inference costs

AI Compiler and Performance Engineer

Applied Machine LearningConfirmed live in the last 24 hours
Full-timeSeattle, WA, USA

About the Job

Requirements

  • A BS, MS, or PhD in Computer Science, Software Engineering, or a related field.
  • Deep experience building compilers, optimizing kernels, or working with machine-learning frameworks at a systems level.
  • Strong proficiency in one or more programming languages such as Python and C++.
  • Strong understanding of one or more of the following: large language model architectures and transformer internals; MLIR, LLVM, XLA, TVM, Triton, or similar compiler infrastructures; GPU, TPU, FPGA, or ASIC compute models, memory hierarchies, and parallel execution; quantization, sparsity, or algorithmic optimization for deep learning.
  • Deep expertise in machine-learning frameworks such as PyTorch, TensorFlow, or JAX, and understanding of machine-learning model deployment challenges.
  • A solid understanding of software engineering best practices, including data structures, algorithms, and testing.
  • A solid understanding of latency, cycles, memory bandwidth, and arithmetic intensity, not just algorithms.
  • Ability to collaborate across machine-learning, hardware, and software disciplines.
  • Ability to thrive in a fast-paced, dynamic startup environment.

Responsibilities

  • Break down large language model and transformer workloads into fine-grained primitives tailored to proprietary compute hardware.
  • Design and implement intermediate-representation transformations, graph optimizations, kernel lowering, and code generation for novel hardware architectures.
  • Collaborate with machine-learning researchers to co-design algorithmic optimizations that yield end-to-end performance gains.
  • Work with hardware architects to refine microarchitectural features, instruction sets, memory hierarchies, and execution models.
  • Build performance models, profiling tools, and benchmarking frameworks to identify bottlenecks and guide design decisions.
  • Prototype and validate improvements across the stack, from PyTorch/XLA-level passes to custom kernel implementations.
  • Contribute to shaping the overall system architecture of an inference engine.

Desired Qualifications

  • PhD in Computer Science, Software Engineering, or a related field.
  • Experience with custom hardware accelerators for machine-learning inference.
  • Contributions to open-source compiler or machine-learning systems projects.
  • Prior startup experience or a background building first-generation systems.

About the Company

ElastixAI

Software platform optimizing AI inference costs

ElastixAI builds a software platform to optimize AI inference for large language models, reducing cost and complexity across cloud and edge deployments. Its hardware-agnostic inference layer adapts to different hardware and workloads, allowing customers to configure for specific use cases and license the tech to chipmakers, cloud providers, and device manufacturers. The product differentiates itself by avoiding lock-in to a single accelerator, instead offering broad compatibility across diverse hardware and leveraging a team with deep experience from Xnor, Apple, and Waymo. The company aims to lower the total cost of ownership per token and enable scalable, affordable AI inference for hyperscalers and enterprises.

Company size
11-50
Company stage
Seed
Total funding
$34M
Headquarters
Seattle, WA
Founded
2025

Recently Posted Jobs

Explore more opportunities at ElastixAI

See more jobs