Prasad Kavuri

Head of AI Engineering · AI/ML Executive Leader

Agentic AILLM PlatformsApplied AI StrategyGlobal Engineering Leadership

Visionary AI/ML executive with 20+ years driving transformative technology strategies across enterprise platforms and AI ecosystems. Currently leading India's first Agentic AI platform (Kruti.ai) at Krutrim, achieving 50% latency reduction and 40% cost savings.

20+

Years Experience

200+

Engineers Led

13K+

B2B Customers

70%

Cost Reduction

AI-Powered Tools

Live demos showcasing agentic AI, semantic search, and open-source LLM orchestration.

🚀Live

RAG Pipeline

Real retrieval-augmented generation with Transformers.js embeddings and ChromaDB — runs entirely in your browser.

Transformers.jsChromaDBnomic-embed-text

Open demo

👥Upgrading

Multi-Agent System

CrewAI-powered agents with real LLM calls via Groq — Analyzer, Researcher, and Strategist collaborating in real time.

Real multi-model routing across Llama 3.1 8B, 70B, and Mixtral — see live latency, cost, and quality trade-offs.

GroqMulti-modelLive latency

Open demo

🔎Upgrading

Vector Search

Semantic search with real sentence-BERT embeddings and UMAP visualisation of the embedding space.

all-MiniLM-L6-v2UMAPCosine similarity

Open demo

🤖Upgrading

AI Portfolio Assistant

Streaming RAG-powered assistant over my experience — ask anything about my background and see retrieved context.

Vercel AI SDKStreamingRAG

Open demo

📄Upgrading

Resume Generator

Paste a job description, get a tailored resume with skill matching scores and selection reasoning.

JD parsingSkill matchingPDF export

Open demo

🎭Upgrading

Multimodal Assistant

Florence-2 image captioning and OCR running in-browser via Transformers.js — no server, no API key.

Florence-2WebGPUIn-browser

Open demo

⚡Upgrading

Model Quantization

Live ONNX benchmark comparing INT8 vs FP32 inference — real file sizes, real latency, real quality diff.

ONNXINT8 vs FP32Transformers.js

Open demo