Loading
Welcome to my portfolio
Specializing in AI Voice Agent platforms, real-time telephony integrations (Pipecat, Daily.co, Twilio), LLM orchestration, and Graph RAG pipelines
Scroll
Featured Work
Key Projects
AI Voice Agents, distributed microservices, event-driven architectures, and real-time streaming applications
01
Product Catalog Voice Agent
Express, FastAPI, Whisper.cpp, Neo4j, Graph RAG, OpenAI
A voice-enabled conversational agent for navigating product user manuals. Features a speech-to-text pipeline using Whisper.cpp integrated with Node.js via WebSocket, a RAG system using Neo4j as a knowledge graph, and a FastAPI backend integrating OpenAI LLMs for contextual response generation.
View Case Study
02
AI-Powered Form Copilot
Next.js, TypeScript, Socket.IO, Google Gemini AI, Node.js, Express
An intelligent form assistant that guides users through data entry via natural conversation, automatically extracting and populating form fields in real-time. Built with WebSocket-based communication between a Next.js frontend and Node.js backend, integrating Google's Gemini AI for conversational form completion.
03
Real-Time Clipboard Sync
Go, WebSockets, Redis Pub/Sub, JWT, PostgreSQL
Cross-platform synchronization backend supporting 1,000+ concurrent users across macOS and Android. Features scalable messaging architecture using Redis Pub/Sub with JWT-based authentication, WebSockets for real-time communication, and PostgreSQL for data persistence.
View Case Study
04
Distributed Rate Limiting System
Go, Docker, Nginx, Redis, Docker Compose
A distributed API gateway with a Go-based rate-limiting microservice, leveraging Redis and a custom Token Bucket algorithm to manage and protect API endpoints. Engineered a scalable microservices architecture using Docker and Nginx for load-balanced request distribution.
View Case Study
05
Distributed Cache Decorator
Python, Redis, Decorators
A Python decorator providing Redis-backed distributed caching with automatic invalidation. Detects code modifications via source code hashing and automatically purges stale cache entries across all application instances, eliminating manual cache management.
View Case Study
Insights & Knowledge
Technical Writing
Deep dives into distributed systems, database internals, performance optimization, and scalability patterns
Article 01
Node.js Streams Internals
This article explores how Node.js streams work under the hood, tracing the complete journey of HTTP request data from network packets to your application code, and response data from your code back to the network. Covers internal buffering, backpressure mechanisms, and the multi-layered architecture that makes streams efficient.
Read Article
Article 02
MVCC, Autovaccume, and Bloat in PostgreSQL
A comprehensive guide to PostgreSQL's Multi-Version Concurrency Control (MVCC) system. Explores transaction IDs, system columns (xmin/xmax), and infomask flags through hands-on examples using pageinspect. Demonstrates how PostgreSQL maintains data consistency across concurrent transactions and explains the role of vacuum in cleaning up obsolete row versions.
Read Article
Article 03
Building a Distributed Rate Limiter with Go, Redis, and Lua
This article discusses building a distributed rate limiter using Go, Redis, and Lua to control the flow of requests, prevent abuse, ensure fair use, and protect backend resources from overload.
Read Article
Article 04
The Idea Behind Fault-Tolerant Systems
An overview of fault-tolerant systems, which are designed to continue operating without interruption despite the failure of one or more of its components
Read Article
Article 05
Why B-trees Can Shorten SSD Lifespan
An article that explains how traditional databases that use B-Trees data structure and indexes can limit the shelf life of Solid States Drives (SSD).
Read Article
Article 06
Understanding Native Graph Databases: Storage and Processing
An explanation of native graph databases, which are optimized for storing and processing graph data. They use index-free adjacency, meaning that each node directly references its adjacent nodes.
Read Article
Article 07
Understanding the Node.js Event Loop
A look into the Node.js event loop, a mechanism that allows Node.js to perform non-blocking I/O operations despite being single-threaded, by offloading operations to the system kernel whenever possible.
Read Article
Article 08
SSTables and LSM-Trees: The Secret Sauce Behind Modern Database Performance
An article detailing SSTables (Sorted String Tables) and LSM-Trees (Log-Structured Merge-Trees), which are used in modern databases to optimize for high-speed read/write operations and handle massive data sets.
Read Article
Article 09
PostgreSQL Indexes, Shared Buffers, and Performance Optimization
Deep dive into PostgreSQL covering indexes, shared buffers, and memory optimization. Learn why column order matters, how to size shared buffers properly, tackle large dataset challenges through partitioning, and understand MVCC's impact on query performance.
Read Article
Get to Know Me
About
Full-Stack Software Engineer specializing in scalable GenAI applications, AI Voice Agent platforms, and production backend systems.
Building real-time conversational AI pipelines with Pipecat, Daily.co, and WebRTC telephony. Expert in LangChain/LangGraph orchestration, Graph RAG systems, and prompt engineering for voice agents achieving sub-500ms latencies.
Master of Science in Computer Science
California State University, Fullerton • 2022 – 2024
Technical Skills
Languages:Python, JavaScript, TypeScript, Go
Backend:FastAPI, Node.js, Express, NestJS, Microservices, gRPC
Frontend:React, Next.js, Redux, Tailwind, WebSockets, SSE
Data Layer:PostgreSQL, MongoDB, Redis, Neo4j, Pinecone
AI/ML Stack:LangChain, LangGraph, Graph RAG, OpenAI, Pipecat
Voice & Telephony:Daily.co, Telnyx, Twilio, WebRTC, SIP
DevOps:Docker, Kubernetes, Kafka, AWS Lambda, Terraform, Jenkins
Certifications
AWS Certified Developer – AssociateApache Kafka 101 by ConfluentOpen Source: Pipecat Flows Contributor
1K+
Daily Users Served
35%
API Response Gains
70+
Students Taught