Senior Principal Software Engineer - LLM Engineering

Senior Principal Software Engineer leading LLM and GNN model serving solutions at JPMorganChase. Responsible for MLOps/LLMOps strategy, optimizing inference, and building scalable platforms on AWS. Collaborates with data science and SRE teams to productionize AI models at enterprise scale.

• Advise and lead strategy for model serving solutions for LLMs and GNNs across cloud and on-premises.
• Define and implement MLOps and LLMOps strategies for end-to-end model lifecycle management.
• Drive optimization of model inferencing using quantization, model parallelism, intelligent batching, and hardware acceleration.
• Create durable, reusable software and platform frameworks to standardize ML Engineering services.
• Establish best practices for automation, CI/CD, and infrastructure-as-code using containerization and orchestration.
• Partner with data science, platform engineering, and SRE teams to productionize models on AWS.
• Lead deployment and optimization using Triton Inference Server and vLLM for high-throughput, low-latency serving.
• Oversee production operations for AI workloads, including monitoring, incident response, security, and compliance.

• 10+ years applied software engineering experience.
• 8+ years AI/ML engineering experience with LLMs, GNNs, and other model architectures (e.g., GPT, Llama, Falcon, Mistral).