Sr GenAI Infra Specialist SA, AWS WWSO Startup

What you'll do

• Advise customers on AI infrastructure choices, including accelerators, cluster topology, storage, networking, cost, and performance.
• Guide customers on distributed training, inference serving, model optimization, profiling, and system tuning.
• Create demos, proof-of-concepts, reference architectures, benchmarks, and technical materials, and collaborate with AWS product and customer teams.

What they ask for

• Experience conveying complex technical concepts to technical and business audiences.
• 8+ years of experience in technology domain areas such as systems engineering, cloud infrastructure, HPC, ML/AI, or distributed computing.
• 3+ years of experience designing, implementing, or consulting on large-scale AI/ML infrastructure, with hands-on GPU-based computing, ML training infrastructure, and inference serving experience.

Nice to have

• Experience deploying LLMs in production on GPUs or other AI acceleration hardware, or experience with CUDA kernels or ML/low-level kernels.
• Experience with production inference platforms, ML container orchestration, HPC schedulers, or fine-tuning and model optimization techniques.

Pay

169,000.00 - 228,600.00 USD annually (base salary); 153,600.00 - 207,800.00 USD annually (base salary); 153,600.00 - 207,800.00 USD annually (base salary)

Tools

AWS, GPU, Trainium, EFA, EKS, SageMaker HyperPod, PyTorch, vLLM

AI focus

Generative AI infrastructure, distributed model training, inference serving and optimization, accelerator profiling, and model tuning techniques.