Senior Principal Software Engineer - LLM Engineering
Core
Architecting and deploying large-scale LLM and GNN solutions for enterprise AI platforms, focusing on inference optimization, model serving, and agentic AI practices.
Role type
Senior Principal Software Engineer (LLM Engineering)
Builds
High-throughput, low-latency model-serving platforms and agentic AI-enabled development frameworks
Domain
Financial Services / AI/ML Engineering
Deliverable
production ML models
Required skills
LLM architecture, GNN, inference optimization, Triton Inference Server, vLLM, PyTorch, TensorFlow, Hugging Face Transformers, LLMOps, MLOps, distributed systems, system design, security governance
Preferred skills
Cloud-native infrastructure (Docker, Kubernetes, Terraform), AI/ML security compliance, trust and safety, payments platform familiarity, open-source contributions, GPU/TPU acceleration, Java
Technologies
AWS SageMaker, Bedrock, EKS, Azure ML, GCP Vertex AI, Triton, vLLM, MLflow, Kubeflow, PyTorch, TensorFlow, Docker, Kubernetes, Terraform, Java
Responsibilities
Lead strategy and architecture for model-serving solutions across cloud and on-premises environments; Implement MLOps and LLMOps approaches for the full model lifecycle; Optimize inference performance using quantization, model parallelism, and hardware acceleration; Establish standards for agentic AI-enabled engineering; Define guardrails for validation, security, and resiliency; Partner with data science and SRE teams to deploy models on AWS; Oversee production operations for AI workloads including monitoring and incident response
Seniority
Principal, strategy & mentorship
