Analytics · AI · Cross-functional
Building AI systems that make analytics self-serve.
Analytics lead with 8+ years across D2C, quick commerce, and edtech — now building LLM-powered tools that automate reporting, detect anomalies, and turn natural language into SQL.
About
What I do
I work across the full analytics stack — from fixing broken event pipelines and rebuilding misaligned fact tables to modelling customer churn and building self-serve data infrastructure for 20+ stakeholders. My focus is on making revenue data reliable, accessible, and decision-ready for every function that needs it.
Most of my work starts with a data problem that looks like a business problem — or a business problem that turns out to be a data problem. After 8+ years across D2C, quick commerce, edtech, and biotech, I've learned to diagnose the difference quickly and fix it at the source, not the dashboard.
I'm now applying that foundation to AI — building LLM-to-SQL pipelines for self-serve analytics, survival models for churn prediction, and automated anomaly detection on the revenue systems I've built. The goal: make the analyst's pattern-recognition work programmable.
Industries
Where I've worked
- SKU-level P&L and multi-brand revenue systems
- Subscription and repeat-purchase analytics
- Churn prediction and retention modelling
- Marketing attribution and channel ROI
- Org-wide data governance and fact tables
- Mobile attribution across AppsFlyer, Mixpanel, CleverTap
- In-app monetisation analytics and inventory fill rates
- Performance marketing channel ROI
- Brand campaign measurement (150+ campaigns)
- Top-of-funnel and mid-funnel conversion diagnostics
- Sales funnel and conversion analytics
- Student lifecycle and engagement tracking
- Revenue and growth reporting
- Early-stage analytics infrastructure
- Revenue and customer data foundation
- Growth and operations reporting
Skills
Technical skills
AI & Automation
LLM-to-SQL Pipelines · RAG on Structured Data · Prompt Engineering · Google Gemini API · LangChain · Firecrawl · Claude Code · Agent Workflows · n8n Orchestration · MCP (Model Context Protocol)
Analytics & Modelling
SQL · Python · R · JavaScript · Cohort Analysis · Regression Models · A/B Testing · Funnel Analytics · Forecasting · Planning · Anomaly Detection
Attribution & Tracking
AppsFlyer · Mixpanel · CleverTap · Amplitude · Branch · Firebase · GTM · Google Analytics · Mobile Event Pipelines
Data Infrastructure
Redshift · Snowflake · BigQuery · DBMS · Google Cloud Platform · Python ETL · Google Sheets API · n8n · cron
BI & Reporting
Looker · Tableau · Power BI · Metabase · Superset · Google Sheets · Excel
Cross-functional
Finance & P&L · Product · Marketing & Growth · Logistics · Operations · Sales · Data Governance · Stakeholder Alignment
Education
Background
2011 – 2016
M.Tech – B.Tech Dual Degree
IIT Kharagpur
Biotechnology & Biochemical Engineering. One of India's premier technical institutions. The scientific foundation informs how I approach measurement, model design, and drawing conclusions from data.
Currently building
Using LLMs to automate revenue analytics — natural language querying on order and customer data, anomaly detection, and AI-generated insight delivery.
See AI projects →AI
AI Projects
NextMove — AI-Powered Idea & Task Manager (iOS)
Personal iOS app that captures ideas, scores them using AI with RVS methodology, generates actionable tasks, and surfaces stale ideas for weekly review.
Why AI: Gemini API scores each idea using RVS methodology and generates 3–6 concrete action steps — turning a raw thought into a prioritized, actionable plan without manual effort.
Price Parity Monitor — Cross-Channel SKU Price Tracker
POC tool that crawls Amazon and Instamart product listings via Firecrawl and surfaces price parity violations against internal D2C prices — per SKU, across channels.
Why AI: Firecrawl extracts price data from dynamically rendered ecommerce pages via a single API — no CSS selectors to maintain across Amazon, Instamart, and D2C layouts.
Conversational Analytics — Natural Language Querying on Customer & Order Data
POC that takes plain English questions about customer behavior and order trends, translates them into SQL, executes the queries, and returns a structured summary answer.
Why AI: An LLM translates a conversational question into one or more SQL queries, executes them against customer and order-level data, and synthesizes the results into a short, readable answer — no SQL required from the user.
Contact
Get in touch
Open to analytics roles, advisory conversations, and collaborations. If you're working on an interesting revenue or growth problem — let's talk.