Skip to content
View hobbytp's full-sized avatar
11 followers · 73 following

Achievements

Achievement: Pair Extraordinairex2Achievement: QuickdrawAchievement: Pull Sharkx2Achievement: YOLOAchievement: Arctic Code Vault Contributor

Achievements

Achievement: Pair Extraordinairex2Achievement: QuickdrawAchievement: Pull Sharkx2Achievement: YOLOAchievement: Arctic Code Vault Contributor

Block or report hobbytp

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.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
hobbytp/README.md

Hi there 👋 I am Peng Tan

  • I worked in Cloud(OpenStack-based), Cloud Native(K8s-based, ServiceMesh), Microservices
  • I’m currently working/learning GenAI: LLM, Context Engineering, Deep Learning, MAS. GenAI System Engineering
  • How to reach me: [email protected]/[email protected]
  • Tech Stack: Python/Typescript/C/C++/Go/Shell, Docker/K8S,LangChain/LangGraph, AutoGen, RAG, Finetuning, Databases, Messagebus, Gateway, Istio, Envoy.

Full-Stack GenAI & Distributed Systems Engineer
From OpenStack & Kubernetes foundations to Multi-Agent (MAS) orchestration and Context Engineering.

🔭 Core Focus:

  • GenAI System Engineering: Retrieval, RAG optimization, prompt/context compression, finetuning (PEFT/LoRA), evaluation.
  • Multi-Agent Architectures: Planning + tool routing + adaptive memory strategies.
  • Cloud Native & Infra: OpenStack, Kubernetes, Service Mesh (Istio/Envoy), microservices resilience.
  • Bridging Infra ↔ AI: Turning distributed platforms into intelligent, automatable systems.
  • Designed end-to-end RAG pipelines (hybrid retrieval + semantic rerank + context window budgeting).

🌱 Selected Strengths:

  • Built MAS prototypes integrating LangGraph + custom evaluators for decision refinement.
  • Experience in performance-tuning service mesh traffic & observability pipelines.

🚀Tech Stack (condensed): Languages: Python, Go, TypeScript, C/C++, Shell
AI: LangChain, LangGraph, AutoGen, RAG, Finetuning
Infra: Kubernetes, OpenStack, Docker, Istio, Envoy
Data & Messaging: PostgreSQL, Redis, Kafka, etc.
Tooling: CI/CD, Observability (Prometheus/Grafana/OpenTelemetry)

Current Exploration:

  • Agent evaluation frameworks
  • Agent RL
  • AI Coding Assistant

📫 Contact: [email protected] | Blog: https://hobbytp.github.io/

Pinned Loading

  1. hobbytp.github.io hobbytp.github.io Public

    Peng Tan's AI Blog

    Jupyter Notebook 3

  2. RD-Agent RD-Agent Public

    Forked from microsoft/RD-Agent

    Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are commi…

    Python

  3. spec-kit spec-kit Public

    Forked from github/spec-kit

    💫 Toolkit to help you get started with Spec-Driven Development

    Python

  4. SuperClaude SuperClaude Public

    Forked from SuperClaude-Org/SuperClaude_Framework

    A configuration framework that enhances Claude Code with specialized commands, cognitive personas, and development methodologies.

    Shell