Skip to content
View def-bgyu's full-sized avatar

Block or report def-bgyu

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
def-bgyu/README.md

💫 About Me:

• Backend Engineer with a strong interest in distributed systems and scalable infrastructure
• Passionate about ML infrastructure, inference optimization, and model serving
• Currently exploring CUDA, GPU programming, and high-performance computing

💻 Tech Stack:

C++ Python AWS Google Cloud React NodeJS FastAPI nVIDIA Flask Django MongoDB Redis Postgres TensorFlow PyTorch GitHub Grafana Docker Kubernetes Jira Prometheus Postman

📊 GitHub Stats:

Pinned Loading

  1. Disaster-Tweet-Classification-Using-Deep-Learning-LSTM-and-BERT Disaster-Tweet-Classification-Using-Deep-Learning-LSTM-and-BERT Public

    Jupyter Notebook

  2. Quantization-and-pruning-as-a-service Quantization-and-pruning-as-a-service Public

    Python

  3. Fleet-OS Fleet-OS Public

    FleetOS — an operating system for AI inference node fleets, handling orchestration, self-healing, and model deployment at scale

    Python

  4. LLM-inference-engine LLM-inference-engine Public

    A production-style LLM inference engine with dynamic batching, async queuing, and Redis semantic caching — inspired by systems like vLLM

    JavaScript