Senior AI Deployment Engineer – Custom Models & Optimization

Amazon Web Services (AWS); Seattle (WA); On-site; USD 168,000 - 227,000; Full time

Job summary

Amazon Web Services, Inc. is seeking a Senior Forward Deployed Engineer to lead embedded engagements with strategic customers. You will shape the customization and optimization of generative AI models, define success metrics, and drive production deployment.

You will balance quality, latency, and cost, while mentoring a team of FDEs and engineers across multiple workstreams. Core responsibilities include architecture of training/inference at scale, data strategy, and collaboration with

Qualifications

• 5+ years of non-internship professional software development experience.
• Mentor, tech lead or leading engineering teams.
• Hands-on experience training, fine-tuning, or optimizing deep learning models.
• Experience communicating technical concepts to senior leadership.

Responsibilities

• Lead the technical engagement as the embedded technical lead for model customization and optimization across multiple workstreams.
• Define the customization strategy to meet quality, latency, and cost targets using prompts, tuning, reinforcement learning, and adapters.
• Architect training and inference systems at scale for large dense and mixture-of-experts models.
• Lead migrations of training and inference workloads to AWS Trainium and optimize kernels.
• Provide technical leadership, code reviews, and mentoring for FDEs and scientists.
• Identify reusable patterns and drive adoption across AWS services.
• Oversee delivery plans, milestones, and risk management with the customer.

Skills

Software development experience

Mentorship

Technical leadership

Communication with leadership

Deep learning model training

Education

Bachelor’s degree in computer science or equivalent

Tools

SGLang

vLLM

TensorRT-LLM

Megatron-LM

PyTorch FSDP2

Miles

verl

NeMo Gym

OpenEnv

Neuron SDK

Job description

Amazon Web Services, Inc. is seeking a Senior Forward Deployed Engineer to lead embedded engagements with strategic customers. You will shape the customization and optimization of generative AI models, define success metrics, and drive production deployment.

You will balance quality, latency, and cost, while mentoring a team of FDEs and engineers across multiple workstreams. Core responsibilities include architecture of training/inference at scale, data strategy, and collaboration with