• Role: Builder — AI & Data Systems
• Education: BITS Pilani, Goa → University at Buffalo (2+2) · B.E. EEE
• Building: Closr
• Focus: Agents · Orchestration · Inference cost · Workflows
• Mantra: Build things that save you money, compute, and time.

Automated multi-source lead engine that scrapes 9+ platforms to identify high-intent B2B signals for the creator economy. Uses a local LLM synthesis layer (qwen2.5:7b via Ollama) to autonomously extract identities and generate pitches. Architected a 4-stage Enrichment Cascade (regex, pattern DBs, headless crawling) to bypass rate limits and maintain a strictly $0/month operating cost.

Palantir-grade intelligence pipeline that scrapes and structures geopolitical data into a Neo4j knowledge graph. Engineered a 2-Layer Resolution Gauntlet using fuzzy matching and all-MiniLM-L6-v2 vector cosine-similarity to disambiguate entities. The entire inference engine is memory-optimized to run within a strict 4GB VRAM ceiling via dynamic context reduction and a rolling keep-alive window.

Secure event ticketing ecosystem that eliminates fraud using TOTP (Time-based One-Time Password) entry mechanisms with 30-second refresh cycles. Implements resale intelligence and smart-contract royalties to track and verify all legitimate ticket transfers. Live on Vercel.

A localized data intelligence platform translating real-world geo-signals into actionable business strategy. Developed a map-based analytics interface using Leaflet, MapTiler, and OpenRouteService. Halted post-prototyping after validating a lack of product-market fit—demonstrating a strict focus on building systems with real business ROI.

Languages:

AI / Data:

Infra / Deployment:

"The best systems are the ones you never notice — because they just work."