Nvidia Senior Applied Machine Learning Engineer NEMO Microservices 

United States, Texas 

175331898

What you'll be doing:

• Development of new generation of Compound AI Systems platform with reasoning capabilities that supports working across multiple modalities including but not limited to images, videos, audio, and text.

• Development of distributed cloud applications, microservices and MLOps platforms able to scale up to huge models

• Creating microservices for task-specific AI cloud services

• Implementing core infrastructure for cloud-native AI training and inference

• Relentlessly pursue speed of light performance under high load

What we need to see:

• BS, Masters, or equivalent experience in computer science, computer architecture, or related field

• 5+ years of experience

• Exceptional coding skills, striving for creating high-quality software

• Ability to work independently, define project goals and scope, interact directly with open-source community, and manage your own development effort

• Experience implementing microservices and cloud-native applications using HTTP REST, gRPC, protobuf, JSON and related technologies

• Experience deploying application on Kubernetes platform, familiarity with helm charts, kustomize, k8s operator.

• Understanding of performance, security, and reliability in complex distributed infrastructure

• Excellent Python or Golang programming and software design skills, including debugging, performance and service health analysis, and test design.

Ways to stand out from the crowd:

• Experience deploying machine learning or statistical models into production environments, especially experience with frameworks such as PyTorch, Tensorflow, ONNX Runtime, and TensorRT

• Background with deep learning frameworks such as Megatron Core, NeMo, HuggingFace Accelerate, HuggingFace Transformers, DeepSpeed, and similar

• Experience with MLOps orchestration platforms such as Seldon Core, Kserve, BentoML and similar

• Experience with inference engines such as VLLM, TensorRT-LLM and similar

• Knowledge of or experience with developing production NLP systems as well as experience working with high availability environments