AI/ML Systems Engineer for AWS Neuron Inference

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 seeks an experienced software engineer to advance inference for Generative AI on AWS accelerators. You will work on distributed inference with PyTorch in the Neuron SDK, tuning models for Trainium and Inferentia, and collaborating across compiler, runtime, and hardware teams.

You will design high‑performance kernels, optimize memory and parallel computing, and contribute to a startup‑like culture that values experimentation and mentorship.

Qualifications

• 3+ years of non‑internship professional software development.
• Bachelor's degree in computer science or equivalent.
• Experience with C++, Python and ML model acceleration.
• Strong knowledge of system performance, memory management and parallel computing.
• Experience debugging and profiling large scale systems.

Responsibilities

• Design, develop, and optimize ML models and frameworks for AWS accelerators.
• Collaborate across compiler, runtime, framework and hardware teams.
• Tune models for highest performance on Trainium and Inferentia.
• Implement high‑performance kernels and ML operations leveraging Neuron.
• Analyze system performance and drive end‑to‑end optimizations.

Skills

C++

Python

PyTorch

LLMs

Machine learning basics

Profiling

Debugging

Performance optimization

Parallel computing

Memory management

Education

Bachelor's degree in CS or equivalent

Tools

CUDA kernels

CUTLASS

JIT compilation

TensorRT

Job description

Annapurna Labs (U.S.) Inc. in Seattle seeks an experienced software engineer to advance inference for Generative AI on AWS accelerators. You will work on distributed inference with PyTorch in the Neuron SDK, tuning models for Trainium and Inferentia, and collaborating across compiler, runtime, and hardware teams.

You will design high‑performance kernels, optimize memory and parallel computing, and contribute to a startup‑like culture that values experimentation and mentorship.