Skip to content
View ericehanley's full-sized avatar
4 followers · 1 following

Achievements

Achievement: Pair Extraordinairex2Achievement: Pull Shark

Achievements

Achievement: Pair Extraordinairex2Achievement: Pull Shark

Block or report ericehanley

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ericehanley/README.md

Hi there, I'm Eric Hanley

I am an AI infrastructure specialist focused on building, scaling, and optimizing machine learning systems. My work primarily revolves around large language models, distributed training, and cloud infrastructure, with a strong emphasis on Google Cloud Platform (GCP) and Kubernetes.

Currently, I am expanding my contributions to open-source projects, particularly in the AI infrastructure, MLOps, and distributed computing ecosystems.

What I am working on

  • Architecting scalable AI infrastructure on Google Kubernetes Engine (GKE).
  • Optimizing LLM serving and distributed training using frameworks like Ray and vLLM.
  • Streamlining cloud resource provisioning and developing infrastructure automation.
  • Identifying and resolving networking bottlenecks in high-performance GPU clusters.

Technologies and Tools

  • Cloud & Infrastructure: Google Cloud Platform (GCP), Kubernetes, GKE, Docker, Bash/Shell scripting
  • AI & Machine Learning: Ray, vLLM, PyTorch, Distributed Training
  • Languages: Python, Shell

Let's Connect

Popular repositories Loading

  1. rightsize-vllm rightsize-vllm Public

    A repository that contains artifacts for rightsizing vLLM.

    Jupyter Notebook 2

  2. tpu-builders-vllm tpu-builders-vllm Public

    Shell 2 1

  3. gke-ray-train gke-ray-train Public

    A series of demos for running training & fine tuning jobs of LLMs on Ray & GKE for distributed workloads.

    Python 1 2

  4. gke-ray-llm-workflows gke-ray-llm-workflows Public

    Forked from anyscale/e2e-llm-workflows

    Fine-tune an LLM to perform batch inference and online serving.

    Python 1

  5. a3-mega-tcpxo-fix a3-mega-tcpxo-fix Public

    A temporary fix for a customer for TCPXO networking.

    1

  6. gpu-recipes gpu-recipes Public

    Forked from AI-Hypercomputer/gpu-recipes

    Recipes for reproducing training and serving benchmarks for large machine learning models using GPUs on Google Cloud.

    Shell