Senior Principal Software Engineer, LLM Engineering

What you'll do

• Lead the strategy and architecture for model serving solutions across cloud and on-premises environments.
• Define and implement MLOps and LLMOps strategies for end-to-end model lifecycle management and governance.
• Optimize model inference for high throughput and low latency using quantization, batching, and hardware acceleration.
• Establish standards for agentic AI-enabled engineering to improve delivery speed, reliability, and code quality.
• Create durable, reusable software and platform frameworks to standardize ML Engineering services across the organization.
• Build and manage production infrastructure using containerization, orchestration, and CI/CD pipelines.
• Partner with cross-functional teams to productionize models on AWS while ensuring observability and cost efficiency.
• Oversee production operations for AI workloads, including monitoring, incident response, security, and compliance.

What we're looking for

• Formal training or certification in software engineering concepts and 10+ years of applied experience.
• 8+ years of AI/ML engineering experience with expertise in LLMs, GNNs, and other model architectures.
• Experience architecting and deploying LLM and GNN solutions on AWS at enterprise scale.
• Hands-on experience building LLM inference engines using Triton Inference Server and vLLM.
• Advanced proficiency in Python and optimization techniques for deep learning frameworks like PyTorch, TensorFlow, and Hugging Face.
• Deep understanding of MLOps/LLMOps tools such as MLflow, SageMaker Pipelines, or Kubeflow.
• Experience designing and scaling agentic AI-enabled development patterns with established governance and security.
• Master’s or PhD in Computer Science, Engineering, or a related field (preferred); experience in trust, safety, or fraud prevention (preferred).