AI systems
Memory Vault
Memory that travels between AI tools, with its history intact.
What one AI tool learns rarely carries into the next — and when it does, nobody can tell where it came from or whether it is still true.
Strands:
00 · Arrival
Building systems where AI, software, and business strategy converge.
Technology & business builderTampa, FloridaFive systems ↓each sits where its strands cross
AI systems
Memory that travels between AI tools, with its history intact.
What one AI tool learns rarely carries into the next — and when it does, nobody can tell where it came from or whether it is still true.
Strands:
Search
Scattered job listings, validated and made searchable.
Listings sit across many sites in many formats, rarely in the form a job-seeker actually needs.
Strands:
Local AI
The whole retrieval loop, running on one machine.
Hosted model APIs hide how extraction, retrieval, and inference actually interact — and keep the data somewhere else.
Strands:
RAG
A focused assistant that knows one corpus well.
A bounded body of career information is only useful if people can question it in their own words.
Strands:
Developer tooling
Working practice, encoded as skills — design, tier, deadman, and a research toolkit.
AI-assisted engineering drifts without discipline: pages ship unverified, expensive models get spent on mechanical work, long sessions die unattended, and research goes unsourced.
Strands:
I am a technology and business builder. Trained as a mechanical engineer, I began in enterprise IT at Tata Consultancy Services, went on to serve as technical advisor and co‑technical head at the startup Samuh Digital, and completed an MBA at the University of South Florida’s Muma College of Business. Today my independent work centers on AI memory and retrieval systems, search tooling, and product experiments — each built with equal regard for technical soundness and practical usefulness.
Tata Consultancy Services · Samuh Digital · MBA, University of South Florida · B.Tech, Mechanical Engineering
The strands unbraid into the tools.
Data, retrieval & AI, AI
FAISS · LanceDB · PostgreSQL · pgvector · vector search · RAG · embeddings · retrieval systems · local LLMs · Ollama · AI agents & agent workflows · prompt & context design
Programming, Software
Python · Java · SQL · JavaScript · TypeScript · R
Front end & back end, Software
React · Next.js · Tailwind CSS · HTML / CSS · Streamlit · WordPress integration · FastAPI · REST / HTTP · API integration
Automation, cloud & tooling, Software
Playwright · Chromium automation · Git · GitHub · Vercel · Cloudflare Pages · Railway · Supabase
Enterprise systems, Business
WebLogic · WinSCP · ITIL incident management · change management · SLA operations · troubleshooting · root-cause analysis
Analytics & business, Business
Excel · Tableau · dashboards · requirements analysis · stakeholder analysis · process improvement · risk assessment · documentation · presentations
Mechanical engineering, origin
SolidWorks · 3D modeling & visualization
From production support to product work to building on my own terms.
June 2021 – November 2022; strands: Software, Business
Associate System Engineer
Enterprise IT and application support inside a large delivery organization: Java, SQL, and WebLogic in production; ITIL-aligned incident and change management under service-level commitments; issue triage, root-cause analysis, documentation, and coordination across teams.
November 2022 – April 2023; strands: Software, Business
Technical Advisor / Co-Technical Head
The other end of the spectrum: a startup, where the work was building websites, refining products and features, identifying and resolving bugs, giving technical direction, and guiding interns through practical delivery.
Ongoing; strands: AI, Software, Business
Independent builder — AI systems and product
AI memory and retrieval systems, search tooling, crawlers and summarizers, retrieval-augmented assistants, research tools, analytics work, and venture experiments — alongside an MBA that added the finance, strategy, and new-venture lens.
MBA; strands: Business
University of South Florida — Muma College of Business · Tampa, Florida
Capstone — Batson-Cook Construction: A strategic analysis built from stakeholder interviews, SWOT, and competitor and business-model analysis, synthesized into recommendations spanning a training academy, client dashboards, subcontractor filtering, market expansion, thought leadership, and AI risk governance.
origin
3D modeling & visualization · SolidWorks · Engineering fundamentals
What it left behind: The habit of designing systems that have to work physically — tolerances, failure modes, and constraints made explicit — which still shapes how I build software.
Open questions are answered fastest by something that runs. A working prototype exposes the real requirements sooner than any document, and it gives everyone the same object to argue about.
Approval flows, permissions, deletion, and the line between what is current and what is past decide whether a system can be trusted. I design those first and treat features as consequences.
Better retrieval, memory, and provenance make AI genuinely useful. The model is the smaller part; the context system around it is where most of the engineering lives.
Measure recall, latency, and cost where they change a decision, and leave the rest alone. Optimization is a choice about what the system is for.
Local versus hosted, recall versus noise, speed versus governance — every design carries a cost. Writing it down is part of the work, not an admission.
A U.S.-focused handicrafts venture built around Indian craftsmanship.
Active concept.
Strands: Software, Business. Next.js · Supabase · Shopify (exploration)
Retrieval and synthesis across an archive of law-review PDFs.
Strands: AI, Software. PDF ingestion · retrieval · search · synthesis