• 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.

Fully autonomous B2B lead generation pipeline built for the creator economy, engineered to run entirely on local hardware (4GB VRAM RTX 3050). Scrapes 7 high-intent web sources and processes the DOM through a 4-stage Extraction Fortress (using CPU-bound bart-large-mnli and all-MiniLM-L6-v2) to aggressively filter noise before a single token touches the GPU. Extracts entities via qwen2.5:7b (Ollama) and routes them through a concurrent 5-thread ReAct Agent state-machine for waterfall email enrichment—maintaining strict $0 cloud LLM costs.

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."