Publications
6
Current preprints and research manuscripts.

Principal Engineer, Independent Researcher
Designing scalable cloud-native systems and practical AI research pipelines for production use.
Exploring reliable LLM systems, cloud-native architecture, and production-ready AI research pipelines.
Software engineer and researcher with 12+ years building large-scale cloud-native systems across enterprise domains. M.S. in Software Engineering (San Jose State University) with deep expertise in AWS microservices, Java, Python, Spring Boot, Docker, Terraform, CI/CD, and data-intensive platforms. Current research focuses on LLMs, RAG, LangChain, and explainable AI to bridge peer-reviewed innovation with production-ready intelligent systems.
Selected publications and preprints across LLM systems, RAG evaluation, and applied AI research.
Loading publication list...
2010
CareerCompleted B.Tech. in Information Technology.
2010 - 2014
CareerWorked across enterprise software programs and core platform delivery.
2014 - 2016
CareerCompleted graduate studies focused on architecture and scalable systems.
2015 - 2016
CareerContributed to big data and platform engineering initiatives.
2016 - 2017
CareerFull-time role building data-intensive systems and production pipelines.
2017 - Present
CareerLeading cloud-native distributed systems and production engineering programs.
Peer Review
Issuer: Web of Science Academy
Online, California, US
View credentialResearcher Academy
Issuer: Elsevier BV (Netherlands)
Amsterdam, North Holland, NL
View credentialPeer Review
Issuer: Association for Computing Machinery
New York, New York, US
View credentialbigocheck
Zero-dependency, AI-assisted Big-O complexity checker. Static analysis + empirical benchmarking for Python.
kvfleet
Production-grade, KV-cache-aware intelligent routing for self-hosted and hybrid LLM fleets.
mcp-egress-guard
Local-first MCP reverse proxy that blocks sensitive, destructive, or policy-violating tool calls before execution using deterministic rules, DLP matchers, and AST-based intent analysis.
mcp-pool
Async connection pool for Model Context Protocol (MCP) client sessions ā keep sessions warm, reuse across requests, auto-reconnect on failure.
mcp-shield-pii
Intercepting gateway proxy for MCP clients/servers ā real-time PII redaction with regex, NLP, and optional subinterpreter concurrency
pdperf
A static performance linter that detects slow Pandas anti-patterns before they reach production.
pydanticforge
Infer robust Pydantic v2 models from messy, evolving JSON streams
schemaglow
Human-friendly schema diff and contract drift detection for CSV, JSON, JSONL, Parquet, OpenAPI, Avro, and protobuf.
toolcallcheck
Deterministic Python testing for tool-using agents. Mock MCP tools, assert exact tool calls and trajectories, verify headers, and run offline in CI.
tracemap
Modern traceroute visualizer for the terminal with TUI, interactive HTML maps, and ASN/GeoIP lookups.
vectormigrate
Python-first tooling for safe embedding-model migration across vector retrieval systems.
promptspecj
A suite of Java libraries for LLM prompt specifications. Includes sub-modules: promptspec-model, promptspec-parser, promptspec-validator, promptspec-runtime, promptspec-codegen-java, promptspec-spring-ai-adapter, promptspec-junit5, and promptspec-maven-plugin.
Selected repositories and research-oriented implementations from my GitHub.
Zero-dependency empirical Big-O complexity checker for Python with CLI, assertions, and pytest integration
A comprehensive framework for evaluating evidence coverage and faithfulness in RAG systems
Official implementation of CoL-CE: A framework for evaluating reasoning validity in RAG systems
š”ļø Real-time PII redaction proxy for MCP (Model Context Protocol) ā detects and masks 23 entity types before they reach the LLM. Drop-in privacy layer for Claude Desktop with zero-latency regex + Nā¦
OpenAPI-style prompt contracts for Java and Spring AI.
Modern traceroute visualization for the terminal and the web. Table-first (MTR-style) output, interactive TUI, HTML/SVG maps, ASN + GeoIP enrichment, replay, diff, and privacy-aware design.
A clean view of my technologies grouped by domain across systems engineering, AI/ML, backend, and cloud delivery.
Distributed platform architecture and runtime reliability.
Applied model, evaluation, and LLM pipeline stack.
Core implementation languages for high-scale services.
Infra automation, orchestration, and delivery platform.
Visible technologies: 22
Have a project, research idea, or collaboration in mind?
Based in San Francisco, USA (Pacific Time (PT)) | Response time: Usually within 24 hours