Ernev Sharma
Germantown, Maryland, United States
Summary
🤩
Rockstar🎓
Top SchoolErnev Sharma is a Machine Learning Engineer with 8 years of experience specializing in taking research-grade models into production at AWS and Amazon Retail. He has shipped scalable GenAI and diffusion inference systems that cut latency by 17× and inference cost by 99% on a 55GB transformer, and led Neuron migrations that delivered 75–85% customer cost savings. Ernev builds repeatable MLOps platforms—designing cross-account model registries, automated CI/CD pipelines, and LLM-powered orchestration that reduced onboarding from 100 developer days to near-touchless deployments. He combines low-level model optimizations (int8 quant, LoRA, torch.compile) with infrastructure design for TB-scale assets across 22–24 regions, closing visibility gaps and saving hundreds of engineering hours. Based in Germantown, MD and trained at University of Maryland, he focuses today on GenAI evaluation, diffusion inference, and agentic MLOps tooling. A practical systems thinker, he’s as comfortable iterating on compiler-level speedups as he is building AI agents to automate the ML lifecycle.
8 years of coding experience
1 year of employment as a software developer
The University of Maryland, College Park
Github Skills (20)
pytorch10
docker10
deploying10
python10
machine-learning-models10
jupyter10
data-science10
mxnet10
machine-learning10
inference10
reinforcement-learning10
sagemaker10
amazon-sagemaker10
mlops10
huggingface10
Programming languages (2)
Github contributions (5)
ErnevSharma/deep-learning-containers
Apr 2024 - Apr 2025
AWS Deep Learning Containers (DLCs) are a set of Docker images for training and serving models in TensorFlow, TensorFlow 2, PyTorch, and MXNet.
Contributions:122 pushes, 20 branches in 11 months
ErnevSharma/amazon-sagemaker-examples
Jun 2023 - Aug 2024
Example 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker.
Contributions:2 pushes, 2 branches in 1 year 2 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.