Building Deployable
AI Systems
Applied AI Engineer focused on RAG, LLMs, semantic search, AI agents, FastAPI, Angular, Firebase, and scalable AI workflows.
Tech Stack / Expertise
AI Infrastructure Control Center
Live telemetry and architectural overview of deployed AI systems, from semantic retrieval to agentic workflows.
RAG Pipeline
Real-time document ingestion, embedding generation, and semantic retrieval for LLMs.
Production-Ready Systems
A showcase of fully deployed, scalable AI architectures and full-stack platforms engineered for real-world impact.
AI Career Intelligence Platform
A scalable job application tracking platform with workflow automation, analytics dashboards, and AI-assisted tracking features. Designed Firestore-backed data pipelines for real-time updates.
Legal Contract Copilot
An auditable enterprise RAG system featuring hybrid search (FAISS + BM25 via RRF), click-to-scroll citation highlights, side-by-side clause comparison matrix, and simulated cloud connectors. Built on a pluggable dual-strategy design supporting local PyTorch models and cloud-hosted API models with automatic fallback.
AI Concepts Playground
Interactive visual explanations of the core machine learning and generative AI architectures powering my projects.
Embeddings & Vectors
System Architecture
High-level data flow and infrastructure blueprints for production pipelines.
Engineering Experience
Building and scaling ML infrastructure at industry-leading enterprises.
Generative AI Engineer (Data Scientist)
Engineered a RAG system using LangChain and LangGraph to process natural language queries across 500K+ banking transactions, reducing manual data retrieval time by 60%. Designed multi-agent LLM workflows for automated credit risk assessment, improving accuracy from 73% to 92%. Deployed OpenAI embeddings with Pinecone semantic search, cutting hallucination rate by 40%.
Associate Data Scientist (ML Engineer)
Developed ensemble ML models (XGBoost, Random Forest) achieving 87% accuracy in readmission prediction. Built end-to-end ML pipelines using Apache Airflow and scikit-learn, cutting model development time from 6 weeks to 2 weeks. Containerized inference services with Docker and deployed on AWS EKS, serving 5K+ daily predictions at <200ms latency.
Data Science Intern
Performed extensive EDA, feature engineering, and assisted in building baseline models for predictive healthcare analytics and supply chain optimization.
Technical Skillset
Comprehensive stack for building end-to-end AI applications and ML infrastructure.
GenAI & LLMs
ML & Data Science
Data Engineering & DBs
MLOps & Automation
Cloud Platforms
Frontend & Analytics
Active Pipelines
What I'm currently engineering and deploying.
AI Resume Screener
Fully deployed semantic matching platform utilizing FastAPI and Sentence Transformers.
AI Career Intelligence Platform
Finalizing the Angular 19 frontend integration with Firebase and NLP microservices.
Legal Contract Copilot
Fully deployed enterprise legal contract RAG platform featuring a pluggable local/cloud architecture and citation highlights.
Ready to scale your
AI Infrastructure?
Currently open to new opportunities. Whether you need a robust RAG pipeline, scalable microservices, or an intelligent agentic workflow—let's build it.