RISHI
CHHABRA

BUILDING THINGS THAT THINK

Machine Learning Engineer • GenAI • RAG • MLOps

Built production RAG systems at Ariesview | M.S. in Machine Learning at Stevens Institute of Technology

Get In Touch Resume View Work

🤖

⚡

🧠

Rishi Chhabra Open to opportunities 📍 New York, NY

ABOUT_ME

🎓 Education

Stevens Institute of Technology

M.S. in Machine Learning

Hoboken, NJ · 2024 – 2026

B.Tech. in Computer Science · Central University of Haryana · 2020 – 2024

💼 Current Role

Ariesview

AI Engineer Intern

RAG & AI Infrastructure

Boston, MA · Sep 2025 – Present

🎯 Focus Areas

GenAI · RAG · MLOps

Production ML Systems

AWS · Kubernetes · Vector DBs

I'm a builder who thrives in early-stage, ambiguous environments. I like owning problems end-to-end—going from a vague idea to something real that people actually use. Speed, judgment, and quality all matter.

💡 Core Principle

"With AI, we can not just get work done, but also make it testable and observable. That combination is magical."

🎯 What Drives Me

End-to-end ownership · Research-to-production · Building reliable AI systems · Developer experience over hype

PYTORCH TENSORFLOW LANGCHAIN RAG LLMS VLLM LORA / QLORA TRANSFORMERS WEAVIATE PINECONE CHROMADB AWS SAGEMAKER LAMBDA DOCKER KUBERNETES CI/CD TERRAFORM MLFLOW PYTHON C++ SQL PROMPT ENGINEERING NLP COMPUTER VISION GRPC NGINX WEIGHTS & BIASES TENSORBOARD PYTORCH TENSORFLOW LANGCHAIN RAG LLMS VLLM LORA / QLORA TRANSFORMERS WEAVIATE PINECONE CHROMADB AWS SAGEMAKER LAMBDA DOCKER KUBERNETES CI/CD TERRAFORM MLFLOW PYTHON C++ SQL PROMPT ENGINEERING NLP COMPUTER VISION GRPC NGINX WEIGHTS & BIASES TENSORBOARD

WORK_I'M_PROUD_OF

⚙️

End-to-End MLOps Pipeline

Academic / Production · AWS SageMaker · Kubernetes · MLflow

Automated ML lifecycle deployment using containerized workflows and Kubernetes orchestration. Integrated MLflow for experiment tracking, reducing manual intervention by 80% and time-to-production by 60%.

MLOPS AWS PRODUCTION

🧠

RAG-Based Q&A System

Python · LangChain · Pinecone · OpenAI

Engineered RAG system processing 10,000+ documents, achieving 85% accuracy and <2s response latency. Implemented hybrid search with Pinecone for balanced keyword/semantic performance.

RAG LANGCHAIN VECTOR DB

🔍

Semantic Search Engine

Weaviate · BERT · FastAPI

Developed semantic search platform for 50,000+ docs with Weaviate, improving relevance scores by 70%. High-performance REST APIs for client dashboards with 99.5% uptime.

SEARCH WEAVIATE BERT

🖼️

Multimodal AI Assistant

PyTorch · Transformers (CLIP) · AWS

Deployed Visual Q&A chatbot using CLIP models, achieving 95% accuracy on custom validation. Scaled to 1,000+ daily interactions via Docker + AWS EC2 deployment.

CV NLP CLIP

WORK_EXPERIENCE

Ariesview

AI Engineer Intern

Boston, MA Sep 2025 – Present

🤖 RAG & AI Infrastructure

Architecting RAG system for internal document processing, integrating Weaviate for hybrid search
Implementing semantic chunking and re-ranking algorithms, improving accuracy by 40% and reducing hallucinations
Optimizing CI/CD pipelines and backend caching using Redis/Valkey, cutting deployment time by 30%

Tech Stack: Weaviate, RAG Pipelines, Redis/Valkey, CI/CD

Incuwise

Software Development Engineer I

Delhi, India Feb 2024 – Aug 2024

📱 Full-Stack & Cloud

Migrated legacy infrastructure to serverless AWS architecture, improving scalability by 60% and ensuring 99.9% uptime
Engineered high-throughput backend services using Node.js/Flutter, reducing API response time by 15% for 10,000+ users
Launched 4 production applications with optimized high-concurrency performance, improving engagement by 25%

Tech Stack: AWS, Node.js, Flutter, Serverless