Sr GenAI Infra Specialist SA, AWS WWSO Startup
Core
Architecting and optimizing large-scale GenAI infrastructure for startup customers on AWS, focusing on model training and inference performance.
Role type
Senior Specialist Solutions Architect (GenAI Infrastructure)
Builds
Scalable, resilient technical architectures for frontier AI model builders using AWS compute, networking, and ML platform services.
Domain
Cloud Infrastructure / Generative AI / High-Performance Computing
Deliverable
production ML models
Required skills
GPU-based computing, distributed training, inference serving, cluster management, performance profiling, cost optimization, technical consulting
Preferred skills
LLM deployment on GPUs/Neuron/TPU, kernel development, container orchestration for ML, HPC schedulers, fine-tuning techniques
Technologies
AWS Trainium/Inferentia, EKS, Kubernetes, SageMaker HyperPod, Slurm, PCS, vLLM, TensorRT-LLM, Triton, PyTorch, JAX, NeMo, NVIDIA Nsight
Responsibilities
Advise customers on AI infrastructure requirements and trade-offs including GPU selection and networking; Provide deep technical guidance on inference and training optimization; Develop demos, proof-of-concepts, and reference architectures; Collaborate with product teams to shape product vision and represent customer voice.
Seniority
Senior, hands-on IC