AI Inference Architect & Performance Engineer

ElastixAI INC.; Seattle (WA); Hybrid; Full time

Benefits offered by this job

Competitive compensation

Comprehensive medical, dental, and vision coverage

Flexible Time Off (FTO)

Paid parental leave

Gym or fitness benefit

Weekly catered lunches in the office

Investment in employee learning & development

Job summary

A pioneering AI startup in Seattle is seeking a Software Engineer for their AI inference platform. This role focuses on optimizing hardware performance through advanced compiler work. Candidates should have a strong background in machine learning frameworks and experience with compiler technologies. The position offers a hybrid work model, where innovative solutions can be developed in a supportive environment. Join a team committed to pushing AI technology to new limits.

Qualifications

• Deep experience building compilers, optimizing kernels, or working with ML frameworks.
• Proficiency in programming languages such as Python and C++.
• Understanding of LLM architectures and transformer internals.
• Experience with GPU/TPU/FPGA/ASIC compute models.

Responsibilities

• Decompose LLM operations into efficient kernel primitives.
• Implement IR transformations and optimizations for novel hardware.
• Collaborate with ML researchers on algorithmic optimizations.
• Develop performance models and profiling tools.

Skills

Compiler building

Kernel optimization

Machine Learning frameworks

Python

C++

MLIR

GPU compute models

Quantization

Software engineering best practices

Education

BS/MS/PhD in Computer Science or related field

Job description

A pioneering AI startup in Seattle is seeking a Software Engineer for their AI inference platform. This role focuses on optimizing hardware performance through advanced compiler work. Candidates should have a strong background in machine learning frameworks and experience with compiler technologies. The position offers a hybrid work model, where innovative solutions can be developed in a supportive environment. Join a team committed to pushing AI technology to new limits.