Engineering Better Decisions

Building decision systems that transform complex operational data into actionable intelligence.

I spent four years helping Fortune 500 OEMs make sense of complex manufacturing data. Today, I'm applying the same systems thinking to build products that transform public and operational data into clear, actionable intelligence.

Whether you're working with operational data, internal documents, or large public datasets, I build decision systems that turn your data into information people can search, understand, and act on.

02

Let's Talk About Your Data

Book a 30-Minute Intro Call

Tell me what you're building, the data you're working with, and where you're getting stuck. I'll review your submission before the call so we can spend our time discussing solutions rather than gathering context.

AvailabilityMonday–Friday | 6:30–9:00 PM IST Response timeWithin 24 hours (after reviewing your request)
Before We Meet
  • Company
  • Industry
  • Website
  • Brief Description
  • Business Problem
  • Current Workflow
  • Dataset Type
  • Number of Datasets
  • Sample Data (Optional)
  • Data Volume
  • Timeline
  • Additional notes
Typical Engagements
  • Conversational analytics on your knowledge base
  • Analytics pipelines for operational data
  • Search across internal documents
  • AI-powered decision systems
  • Custom data applications built around your workflows
03

Build Log

#publyq01 Live
Publyq: Intelligence Layer for Public Grievance Data
Solution

Publyq transforms raw public grievance records into a searchable civic intelligence layer. By combining data enrichment, geospatial mapping, and conversational analytics, it helps users understand what is happening across a city instead of searching through thousands of individual complaints.

Proof / Metrics
200 Wards Covered
3.4k+ Complaints Indexed
23 Constituencies Mapped
How It Works
Public Complaints Data Enrichment Ward Mapping Knowledge Layer Conversational Analytics Insights & Decisions
Tech
  • FastAPI
  • PostgreSQL
  • Gemma4
  • Python
  • JavaScript
#kashiq01 in progress
Kashiq: Multi-Account Financial Intelligence
Solution

Kashiq automatically parses bank statements, categorises transactions, and combines multiple accounts into a single, searchable view of personal finances with intelligent transaction clustering.

How It Works
Statement Upload Parser Normalization Auto-Clustering Dashboard Aggregation Runway Forecast User Validation
Status

Strengthening the parsing and auto-clustering engine to enable multi-format document ingestion (PDF, CSV, XLSX) and MECE-based transaction classification.

Tech
  • Python
  • Flask
  • pandas
  • React
  • Vite
  • Recharts
04

Track Record

Lead Analytics · Axion Ray (Vertical AI) · Apr 2022 – Apr 2026
Scaled enterprise analytics across product, operations, and AI workflows for one of Axion Ray's largest customer portfolios.
$15M+quality losses
Built analytics workflows that surfaced over $15M in potential quality losses by identifying recurring engine failure patterns across warranty claims, work orders, and service escalations, enabling engineering teams to prioritize corrective actions.
26%of revenue
Served as the end-to-end analytics lead for one of Axion Ray's largest enterprise accounts, representing approximately 26% of company revenue, coordinating delivery, client priorities, and analytics operations across cross-functional teams.
90%ETL automation
Designed and deployed Python and LLM-powered automation pipelines that eliminated approximately 90% of manual ETL effort for failure-code extraction, reducing processing time while improving data consistency.
24analysts
Led and mentored a team of 24 analysts, standardizing workflows, reducing delivery bottlenecks, and improving delivery quality across multiple workstreams.
450+client users
Measured product adoption and engagement across an enterprise AI platform serving more than 450 client stakeholders, designing funnel analyses, WAU/MAU reporting, and feature-flag experiments that informed product strategy and operational decisions.
05

Preferred Stack

Languages
  • Python
  • SQL
  • JavaScript
Data
  • PostgreSQL
  • Pandas
  • NumPy
  • GeoPandas
Backend
  • FastAPI
  • Flask
  • Pydantic
Frontend
  • React
  • Vite
  • Tailwind CSS
  • Recharts
AI
  • Gemma
  • Ollama
  • RAG
  • Vector Search
Infrastructure
  • Cloud Run
  • Cloud SQL
  • Vercel