Senior AI Engineer, NeMo Retriever - Model Optimization and MLOps

View full description

Requirements:

• Python programming expertise with Deep Learning (DL) frameworks such as PyTorch.
• Experience delivering software in a cloud context and is familiar with the patterns and processes of handling cloud infrastructure
• Knowledge of MLOps technologies such as Docker-Compose, Containers, Kubernetes, Helm, data center deployments, etc.
• Familiarity with ML libraries, especially PyTorch, TensorRT, or TensorRT-LLM.
• Excellent in-depth hands-on understanding of NLP, LLM, MLLM, Generative AI , and RAG workflows

Responsibilities:

• Develop and maintain NIMs that containerize optimized models using OpenAPI standards using Python or an equivalent performant language.
• Work closely with partner teams to understand requirements, build & evaluate POCs, and develop roadmaps for production-level tools
• Enable development of integrated systems - AI Blueprints that provide a unified, turnkey experience.
• Help build and maintain our Continuous Delivery pipeline with the goal of moving changes to production faster and safer while ensuring key operational standards.
• Provide peer reviews to other specialists, including feedback on performance, scalability, and correctness.