Annapurna Labs (U. S. ) Inc.

Technology

SoftwareDevelopmentEngineer-AI/ML,AmazonNeuron,MultimodalInference

$144–194k Seattle, Washington, United States FULL TIME
Market Sentiment
HIGH DEMAND

Neural analysis suggests this role is
optimal for Mid+ candidates.

The Brief

“Software Development Engineer - AI/ML, Amazon Neuron, Multimodal Inference at Annapurna Labs (U. S. ) Inc.. Skills: AI/ML, Amazon Neuron, Multimodal Inference, High-performance computing. Lead efforts in building distributed inference support. Tune models for highest performance”

What You'll Achieve.

Achieve optimal performance; Maximize performance; Ensure optimal performance; Drive efficiencies in software architecture

Industry & Context.

Technology
Problems you'll solve

Debugging performance issues; Troubleshooting

What They're Looking For.

Must Have

3+ years software development experience, 3+ years system design/architecture experience, Fundamentals of Machine learning and LLMs, Software development in C++ or Python, Understanding of system performance, Understanding of memory management, Understanding of parallel computing principles, Proficiency in debugging, Proficiency in profiling, Implement best software engineering practices

Nice to Have

Familiarity with PyTorch, Familiarity with JIT compilation, Familiarity with AOT tracing, Familiarity with CUDA kernels, Familiarity with ML kernels, Familiarity with low-level kernels, Performant kernel development experience, Familiar with Triton syntax, Familiar with Triton tile-level semantics, Experience with online inference serving, Experience with offline inference serving, Deep understanding of computer architecture, Deep understanding of operation systems level software, Working knowledge of parallel computing

What You'll Do.

Lead efforts in building distributed inference support

Tune models for highest performance

Maximize efficiency on silicon

Develop and optimize ML models

Optimize ML frameworks

Deploy models on ML hardware

Participate in ML system development

Design distributed computing architecture

Implement distributed computing architecture

Profile ML system performance

Optimize ML system performance

Test ML system performance

Deploy ML system performance

Build infrastructure to analyze models

Build infrastructure to onboard models

Design high-performance kernels

Implement high-performance kernels

Leverage Neuron architecture

Leverage Neuron programming models

Analyze system-level performance

Optimize system-level performance

Conduct performance analysis

Identify performance bottlenecks

Resolve performance bottlenecks

Implement fusion optimizations

Implement sharding optimizations

Implement tiling optimizations

Implement scheduling optimizations

Conduct comprehensive testing

Perform end-to-end model testing

Deploy through pipelines

Enable customer ML models

Optimize customer ML models

Develop innovative optimization techniques

Debug performance issues

Optimize memory usage

Shape inference stack

Design software architecture efficiencies

How You'll Work.

Team & Collaboration

Cross-functional team; Compiler engineers; Runtime engineers; Hardware teams; Applied scientists; System engineers; Product managers; Open source ecosystems

Process & Methodology

Agile

Full Job Description

The Annapurna Labs team at Amazonbuilds AWS Neuron, the software development kit used to accelerate deep learning and GenAI workloads on Amazon’s custom machine learning accelerators, Inferentia and Trainium. The AWS Neuron SDK, developed by the Annapurna Labs team at AWS, is the backbone for accelerating deep learning and GenAI workloads on Amazon's Inferentia and Trainium ML accelerators. This comprehensive toolkit includes an ML compiler, runtime, and application framework that seamlessly integrates with popular ML frameworks like PyTorch and JAX enabling unparalleled ML inference and training performance. The Inference Enablement and Acceleration team is at the forefront of running a wide range of models and supporting novel architecture alongside maximizing their performance for AWS's custom ML accelerators. Working across the stack from PyTorch till the hardware-software boundary, our engineers build systematic infrastructure, innovate new methods and create high-performance kernels for ML functions, ensuring every compute unit is fine tuned for optimal performance for our customers' demanding workloads. We combine deep hardware knowledge with ML expertise to push the boundaries of what's possible in AI acceleration. As part of the broader Neuron organization, our team works across multiple technology layers - from frameworks and kernels and collaborate with compiler to runtime and collectives. We not only optimize current performance but also contribute to future architecture designs, working closely with customers to enable their models and ensure optimal performance. This role offers a unique opportunity to work at the intersection of machine learning, high-performance computing, and distributed architectures, where you'll help shape the future of AI acceleration technology You will architect and implement business critical features, and mentor a brilliant team of experienced engineers. We operate in spaces that are very large, yet our teams remain small an

Free ATS check

Applying for this Software Development Engineer - AI/ML, Amazon Neuron, Multimodal Inference role?

Most applicants get filtered before a human reads their resume. See if yours makes the cut.

ANONYMOUS · UNFILTERED

What do employees actually say about Annapurna Labs (U. S. ) Inc.?

Real rants from real employees. Read before you apply.

Read Company Rants →