Skip to content
View FilledVaccum's full-sized avatar

Highlights

  • Pro

Block or report FilledVaccum

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 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
FilledVaccum/README.md

Hi, I'm Swapnil Tiwari πŸ‘‹

GenAI Solutions Architect @ AWS | AI/ML Builder | LLM Engineer

LinkedIn GitHub


πŸš€ Live Projects on Vercel

Project Description Link
Hugging Brain AI intelligence platform for engineers β€” curated insights on LLMs, VLMs, GenAI, and Agentic AI huggingbrain.in
RedForge Production-grade LLM Red Teaming & Vulnerability Scanner β€” 47 probes, 9 providers, OWASP LLM Top 10, MITRE ATLAS, compliance reports redforge.vercel.app
Prompt Battle Competitive prompt engineering arena β€” battle, practice, context challenges & superpowers. Powered by Claude Haiku prompt-battle-pi.vercel.app
Claude Architect Lab Interactive lab for learning Claude API patterns, architecture, and best practices claude-architect-lab.vercel.app
Inference Engineering Guides and tools for LLM inference optimization and deployment inferenceengineering-tech.vercel.app

πŸ“‚ Recent GitHub Projects (2024–2026)

πŸ€– AI / LLM Tools & Applications

Repo Description
redforge Production-grade LLM Red Teaming & Vulnerability Scanner β€” OWASP LLM Top 10, MITRE ATLAS, YARA scanner
hugging-brain Hugging Brain β€” AI intelligence hub for engineers covering LLMs, VLMs, GenAI and Agentic AI
prompt-battle Competitive prompt engineering arena powered by Claude Haiku
LLM-Inferencing-Recommender Tool to help decide the right GPU for LLM inference workloads
building-with-claude-api Code samples and patterns for building with the Claude API
claude-with-amazon-bedrock Crash course on using Claude with Amazon Bedrock
sample-agents-with-nova-act-and-mcp Build web-action agents combining Amazon Nova Act with Model Context Protocol (MCP)

πŸ“š Courses & Learning

Repo Description
NCP-AAI Complete prep package for NVIDIA-Certified Professional: Agentic AI β€” 32 notebooks, 112 practice questions, 5 labs
Building-Agentic-AI-Applications-with-LLMs Comprehensive course for NVIDIA NCP-AAI certification
rag-evaluation-course Course on evaluating RAG and semantic search systems
LearningLangChain_v1.0 Learning LangChain v1.0 and building agents
LLMsFromScratch Building large language models from scratch
Learning-PyTorch PyTorch fundamentals and deep learning experiments

πŸ”¬ Research & Experiments

Repo Description
gpt-2 Training GPT-2 from scratch on tinyshakespeare with MLflow tracking β€” inspired by Andrej Karpathy
gpt-2-hindi Training GPT from scratch on FineWeb Hindi-Latin dataset with MLflow
rag-cookbook Recipes and patterns for Retrieval-Augmented Generation
fastapi-for-machine-learning FastAPI patterns for serving ML models
Inference-Engineering Deep dive into LLM inference engineering

πŸ› οΈ Tools & Infrastructure

Repo Description
Swapnil-Portfolio Personal portfolio website built with Astro
nvidia-agent-toolkit NVIDIA agent toolkit exploration and experiments
q_cli_prompt_template Amazon Q CLI prompt templates
MindMaps Visual mind maps for AI/ML concepts

🧰 Tech Stack

Python TypeScript Next.js AWS PyTorch FastAPI


Building at the intersection of cloud infrastructure and AI β€” one model at a time.

Pinned Loading

  1. FilledVaccum FilledVaccum Public

  2. gpt-2 gpt-2 Public

    Training gpt from scratch using tinyshakespeare dataset and using mlflow to track the training metrics - Inspired by andrej

    Jupyter Notebook

  3. gpt-2-hindi gpt-2-hindi Public

    Training gpt from scratch using fineweb hindi_latin textual dataset and using mlflow to track the training metrics - Inspired by andrej

    Jupyter Notebook

  4. LLM-Inferencing-Recommender LLM-Inferencing-Recommender Public

    It's hard to decide the GPU to run LLM Inferencing, building this tool to make the job easier

    TypeScript 2

  5. MindMaps MindMaps Public

    MindMaps

  6. Learning-PyTorch Learning-PyTorch Public

    Jupyter Notebook 1