Skip to content
View Kumaresan-AI-Engineer's full-sized avatar
2 followers · 4 following

Block or report Kumaresan-AI-Engineer

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
Kumaresan-AI-Engineer/README.md

👋 Hi, I'm Kumaresan

GenAI Engineer | LLM Systems | FastAPI | RAG | Agents

I build production-grade GenAI systems — document intelligence, LLM agents, and scalable AI backends.

💻 Tech Stack (GenAI / LLM Engineer)

🧠 GenAI & LLM Providers

OpenAI Anthropic Gemini Mistral Cohere Groq Grok Hugging Face Ollama Together AI DeepSeek Meta Llama Perplexity AI AI21 Labs Replicate Fireworks AI Cerebras

☁️ AI Cloud Platforms

AWS Bedrock Azure OpenAI Vertex AI Amazon SageMaker

🔗 LLM Frameworks & Orchestration

LangChain LangGraph LlamaIndex Haystack Semantic Kernel DSPy CrewAI AutoGen PydanticAI Agno Smolagents OpenAI Agents SDK Instructor Outlines

🤖 Agentic Protocols & Standards

MCP A2A Protocol Computer Use

📄 Document Intelligence & OCR

Amazon Textract Google Document AI Azure Document Intelligence Surya OCR Docling EasyOCR Tesseract PaddleOCR Unstructured PDF Processing PyMuPDF Marker Camelot LlamaParse

🗄️ Vector Databases & Embeddings

Pinecone Weaviate Qdrant ChromaDB FAISS Milvus pgvector Elasticsearch LanceDB Vespa MongoDB Atlas Vector

🔍 Search & Retrieval Tools

Tavily SerpAPI Brave Search Exa AI OpenSearch

🧠 Memory & Caching

Mem0 Zep GPTCache Prompt Cache

🤖 ML/DL Frameworks

PyTorch TensorFlow Transformers scikit-learn Keras spaCy NLTK Sentence Transformers

⚙️ Model Serving & Inference

vLLM SGLang TensorRT ONNX Triton BentoML Text Generation Inference LiteLLM

🎯 Fine-tuning & Training

LoRA QLoRA PEFT Unsloth Axolotl DeepSpeed TRL RLHF DPO GRPO Mergekit

📊 LLM Observability & Evaluation

LangSmith Langfuse Weights & Biases MLflow Arize AI Phoenix Deepeval RAGAS OpenLLMetry Helicone Braintrust PromptLayer Comet ML

🧩 Backend, APIs & Realtime

Python FastAPI Flask AsyncIO Pydantic REST API GraphQL gRPC WebSocket WebRTC SSE

🗃️ Databases

MongoDB PostgreSQL MySQL SQL Server Redis SQLite DynamoDB Neo4j

📨 Message Queues & Streaming

Celery RabbitMQ Apache Kafka Amazon SQS Pub/Sub

☁️ Cloud Platforms

AWS GCP Azure

🐳 DevOps & Infrastructure

Docker Kubernetes Terraform GitHub Actions GitLab CI Jenkins Nginx

🎙️ Voice & Audio AI

OpenAI Whisper ElevenLabs AssemblyAI Deepgram Amazon Polly Google TTS

🖼️ Vision & Image AI

OpenAI Vision Gemini Vision DALL·E Stable Diffusion Flux Midjourney CLIP ColPali OpenCV YOLO

🎨 UI & Demo Tools

Streamlit Gradio Chainlit React Next.js

🛠️ Development Tools

Git GitHub VS Code Cursor Jupyter Postman pytest

📦 Data Processing & Analysis

Pandas NumPy Polars Apache Spark Dask

🔐 Security & Auth

JWT OAuth Auth0 API Keys

🛠️ GenAI Best Practices

Prompt Engineering RAG Graph RAG Multimodal RAG Self-RAG Corrective RAG Agentic AI Multi-Agent Systems Function Calling Tool Use Structured Output Hallucination Control Context Management Long Context LLM Evaluation Guardrails Chunking Strategies Hybrid Search Reranking Semantic Caching

🚀 What I Build

  • 📄 LLM-powered document intelligence (OCR + extraction + validation)
  • 🤖 Agentic AI systems (LangGraph, CrewAI, ReAct, tool calling)
  • 🔍 Advanced RAG pipelines (hybrid search, reranking, multi-modal)
  • ⚡ Async, scalable FastAPI backends with streaming support
  • 🎙️ Voice AI applications (STT/TTS pipelines)
  • 📊 LLM observability & evaluation frameworks
  • 🔧 Fine-tuned models for domain-specific tasks
  • 🧪 Reliable AI systems with evaluation, guardrails & retries

Popular repositories Loading

  1. Kumaresan-AI-Engineer Kumaresan-AI-Engineer Public

  2. Outbound_Ai Outbound_Ai Public

    Make outbound calls directly from your browser with real-time AI transcription, post-call analysis, smart follow-up reminders, and a full analytics dashboard — all powered by Groq AI.

    JavaScript

  3. Git_Ai Git_Ai Public

    Python

  4. Scrapegraph-ai Scrapegraph-ai Public

    Forked from ScrapeGraphAI/Scrapegraph-ai

    Python scraper based on AI

    Python

  5. llama_index llama_index Public

    Forked from run-llama/llama_index

    LlamaIndex is the leading document agent and OCR platform

    Python

  6. tavily-python tavily-python Public

    Forked from tavily-ai/tavily-python

    The Tavily Python SDK allows for easy interaction with the Tavily API, offering the full range of our search, extract, crawl, map, and research functionalities directly from your Python programs. E…

    Python