Full Stack & AI Engineer · Compliance Platforms · Agentic Systems · Data Pipelines · Faridabad
I build compliance platforms, agentic systems, and data pipelines that ship fast and scale cleanly.
Currently at OnFinance AI as a Full Stack Engineer, building role-based dashboards, regulatory workflows, analytics APIs, and AI agent systems for compliance teams.
- Built the frontend from scratch with Next.js, TypeScript, and Tailwind CSS
- Optimized analytics APIs on 300k+ MongoDB records, cutting dashboard response times from 4.5-6 min to 15-30 sec
- Migrated AI agent architecture to a Deep Agents framework with skill-based routing
- Partnered with the executive team to support a $4.2M pre-Series A round from PeakXV Partners
| Metric | Focus |
|---|---|
| 30x | Faster dashboard delivery, from 4.5-6 min to 15-30 sec on 300k+ records |
| 90%+ | Data extraction accuracy, up from ~20% with ML-assisted validation |
| $4.2M | Pre-Series A funding round supported from PeakXV Partners |
| 10 days | Compliance platform MVP from ingestion to evaluation to audit |
Full Stack Engineer · Remote · Nov 2024 - Present
- Built the entire frontend from scratch with Next.js, TypeScript, and Tailwind CSS, delivering role-based dashboards and regulatory workflows that enabled compliance teams to process cases 30% faster.
- Optimized analytics APIs on 300k+ MongoDB records via multi-stage aggregation pipelines, cutting dashboard response times from 4.5-6 min to 15-30 sec.
- Migrated AI agent architecture to a Deep Agents framework with skill-based routing, reducing deployment time by 70% and consolidating 47 specialized tools into 8 reusable sub-agents.
Backend Engineering Intern · Remote · Feb 2024 - Jul 2024
- Built FastAPI + Python pipelines that extracted structured financial data from PDFs using computer-vision and NLP models.
- Improved LinkedIn profile validation accuracy from ~20% to 90%+ with rule-based and ML-assisted validation logic.
- Fine-tuned Meta LLaMA-3 models for internal AI automation workflows and built DOCX and PPTX report generation pipelines from structured JSON inputs.
AI Systems / Full Stack Consultant · Remote
- Co-built a production-ready AI agent compliance validation platform MVP in 10 days, covering regulation ingestion, reviewer workflows, real-time violation surfacing, and PDF audit reporting.
- Architected a multi-stage regulation ingestion pipeline with Mistral OCR, GPT semantic chunking, knowledge-graph triple/ENM extraction, and Qdrant vector indexing.
- Delivered React + TypeScript reviewer dashboards for flag triage, cited regulatory evidence, transcript replay, and audit export.
| Project | Description | Stack |
|---|---|---|
| LexiKing | AI-powered vocabulary tracker with spaced repetition and adaptive quiz generation. Replaced a traditional FastAPI + MongoDB + WebSocket stack with Convex's reactive database. Metric: ~60% less server-side code |   |
| AI Compliance Platform | Real-time compliance validation system for AI agent conversations. Detects regulatory violations turn-by-turn and surfaces corrective guidance before the agent's next reply. Metric: Full MVP in 10 days |    |
| Supabase Open Source | Contributed logo and dark-mode display fixes across Supabase documentation and the main website. Metric: Shipped to production |   |
Frontend
Backend
Data & AI
Databases & Tools
[BUILDING] compliance platforms
[DESIGNING] reviewer-grade dashboards
[EXPLORING] agentic workflows
[SHIPPING] full-stack AI products