class ChaitanyaSaiKurapati:
def __init__(self):
self.role = "AI/ML Engineer | Full-Stack Developer"
self.education = "B.Tech CSE @ Amrita Vishwa Vidyapeetham (2022–2026)"
self.cgpa = 8.47
self.focus = ["LLMs", "RAG Architectures", "Distributed Systems", "Production ML"]
self.publications = ["ICCATEET 2026", "IEEE INDISCON 2025"]
self.leetcode = "250+ problems solved | Top 15%"
self.motto = "Ship to production, not just notebooks."
def current_work(self):
return "AI-powered Resume Intelligence @ Alpxin Technologies"
def ask_me_about(self):
return ["LangChain", "FAISS", "FastAPI", "PyTorch", "Apache Spark"]| 🎯 Metric | 🚀 Result |
|---|---|
| Resume–Job Matching Accuracy | 80% with Sentence Transformers + FAISS |
| Medical Imaging Classifier | 94.2% accuracy / 0.96 AUC (Published) |
| RAG Hallucination Rate | Reduced from 34% → 8% |
| Distributed Pipeline Throughput | 4× improvement on 1M+ records/day |
| URL Shortener Load | 50K concurrent requests handled |
| Malware False Positives | −20% via NLP-based approach |
| AutoML Experiment Time | < 3 minutes end-to-end |
| Project | Description | Stack | Highlight |
|---|---|---|---|
| 🧠 AI Resume Intelligence | NLP-based resume–job matching system | FastAPI · FAISS · Sentence Transformers · Streamlit | 80% match accuracy |
| 📄 Smart Document Assistant (RAG) | Production RAG pipeline with minimal hallucination | LangChain · FAISS · OpenAI · Python | 34% → 8% hallucination |
| 🔗 Scalable URL Shortener | High-throughput distributed shortener | Flask · Redis · MySQL | 50K concurrent requests |
| ⚡ AutoML Platform | Automated model selection & hyperparameter tuning | Scikit-learn · Python | <3 min experiments |
| 📊 Distributed Data Pipeline | Large-scale Spark ETL pipeline | PySpark · Apache Spark · AWS S3 | 1M+ records/day, 4× throughput |
| 🏥 Chest X-Ray Disease Detection | Multi-label classification using Vision Transformers | PyTorch · Vision Transformer · DenseNet | 94.2% accuracy · 0.96 AUC |
| 🛡 Malware Detection via LLMs | LLM-enhanced static analysis for malware | NLP · Transformers · Python | −20% false positives |
|
ICCATEET 2026
|
IEEE INDISCON 2025
|
🥇 Hackathon Finalist — Top 8 out of 120 teams | 💻 250+ LeetCode problems — Top 15% globally
👨🏫 Mentored 15+ students in Data Structures & Algorithms | ✍️ Published technical articles on AI & ML
📖 2× Peer-Reviewed Publications (IEEE + ICCATEET) | ⚡ AI/ML Intern @ Alpxin Technologies
- 🎯 Built an AI-powered Resume Intelligence System achieving 80% accuracy in job-to-resume matching
- 🔍 Improved resume parsing and semantic similarity using Sentence Transformers + FAISS
- 🧩 Designed a skill-gap detection pipeline leveraging LLMs for targeted candidate feedback
- 🚀 Deployed end-to-end scalable system using FastAPI + Streamlit with production-ready architecture
┌──────────────────────────────────────────────────────────┐
│ 🔭 Scalable ML systems for production workloads │
│ 🧪 Advanced LLM + RAG architectures │
│ ☁️ Cloud-native AI deployment (AWS + Docker) │
│ 📊 Distributed data engineering with Apache Spark │
│ 🎓 Graduating May 2026 — Open to MLE / SDE Roles │
└──────────────────────────────────────────────────────────┘
I'm always open to collaborating on AI/ML projects, discussing research ideas, or exploring full-time opportunities.
"The best model is the one that's running in production."
⭐ If you find my work valuable, consider starring a repo — it means a lot!