Senior SDE — Neuron Inference & LLM Optimization

Amazon Web Services (AWS); Seattle (WA); On-site; USD 144,000 - 194,000; Full time

Benefits offered by this job

Health insurance

401(k) matching

Paid time off

Parental leave

Job summary

Annapurna Labs (U.S.) Inc. in Seattle, WA is seeking a senior software engineer for the Machine Learning Inference Applications team.

You will develop and optimize core building blocks of LLM Inference on Neuron devices, including Attention, MLP, Quantization, and more, working with chip, compiler, and runtime teams. You will adapt recent research in LLM optimization to Neuron chips, aiming for best performance across open source and internal models, and participate in thorough code reviews and

Qualifications

• Minimum 3+ years of non-internship professional software development experience.
• 2+ years in design or architecture of large-scale systems.
• 1+ years of software development engineer experience.
• 1+ years designing multi-tiered, multi-threaded, distributed software.
• 1+ years of OO design experience.
• Bachelor's degree in CS, Engineering, Math, or related field.

Responsibilities

• Adapt latest research in LLM optimization to Neuron chips to extract best performance.
• Collaborate across teams and organizations to drive performance and accuracy.

Skills

Software development

Design/architecture

Object Oriented Design

Distributed systems

C++

Java

C#

Perl

Education

Bachelor's degree in Computer Science or related field

Bachelor's degree in CS (preferred)

Tools

C#

C++

Java

Perl

Job description

Annapurna Labs (U.S.) Inc. in Seattle, WA is seeking a senior software engineer for the Machine Learning Inference Applications team.

You will develop and optimize core building blocks of LLM Inference on Neuron devices, including Attention, MLP, Quantization, and more, working with chip, compiler, and runtime teams. You will adapt recent research in LLM optimization to Neuron chips, aiming for best performance across open source and internal models, and participate in thorough code reviews and