Skip to content
View Sanjay-00's full-sized avatar
👾
Building
👾
Building

Block or report Sanjay-00

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Sanjay-00/README.md

Building Reliable Systems That Remove Operational Bottlenecks


About Me

I'm an Applied AI Engineer and Portfolio Analytics professional at Shriram Finance.

I enjoy understanding how people work, identifying recurring operational bottlenecks, and building reliable systems that eliminate them.

Most of the systems I've built started as real problems I encountered at work, repetitive reporting, manual document processing, underwriting workflows, and analytical requests that consumed valuable time.

My engineering approach is simple:

  • Understand the workflow.
  • Find the recurring friction.
  • Design a reliable solution.
  • Use AI only where it genuinely adds value.

I'm currently building AI-assisted systems for lending, portfolio analytics, and workflow automation.

Open to Applied AI Engineer, AI Engineer, GenAI Engineer, Analytics Engineer, and Data Analyst opportunities.


Engineering Philosophy

Technology should follow the problem, not the other way around.

I believe deterministic systems should handle anything requiring correctness, while AI should be responsible for language understanding and reasoning, not inventing business metrics.

Across almost everything I build, the goal is the same:

Reduce the time between information and business decisions by removing recurring operational bottlenecks.


🛠️ Tech Stack

Languages & Analytics

AI & Agentic Systems

Backend & Deployment

Cloud & Data Platforms

Document Intelligence


Featured Projects

CollectionIQ • Portfolio Intelligence Platform

The Problem

Collection leaders repeatedly depended on analysts for portfolio summaries, KPI tracking, branch comparisons, and ad hoc analytical requests. Preparing those insights often took hours.

The Solution

CollectionIQ is a portfolio intelligence platform that enables business users to explore lending portfolios using natural language.

Instead of relying on an LLM to calculate business metrics, it separates language understanding from numerical computation. AI interprets user intent, while deterministic analytics compute every KPI through validated business logic.

Impact

  • Used daily by business leaders
  • Reduced portfolio insight turnaround from hours to under one minute
  • Eliminated repetitive analytical requests
  • Enabled self-service portfolio exploration using natural language

Tech Stack

PythonLangGraphPandasGemini APIStreamlitLangSmith


FinSight • AI-Assisted Underwriting Intelligence

The Problem

Underwriters spend significant time validating borrower information, reviewing bureau reports, and preparing credit assessments.

The Solution

FinSight combines deterministic underwriting rules with AI-assisted reasoning. Rule-based validations ensure correctness, while AI provides contextual risk summaries and grounded borrower Q&A.

Impact

  • Automated 15 underwriting validations
  • Reduced manual underwriting review effort
  • Improved consistency of credit assessment workflows
  • Human-in-the-loop decision support

Tech Stack

PythonLangChainGemini APIPyMuPDFStreamlit


AutoCAM • Automated Bureau Processing

The Problem

Loan officers manually extracted hundreds of loan accounts from bureau reports before underwriting could even begin.

The Solution

AutoCAM automates bureau extraction, validates outputs against bureau summaries, and uses AI only when deterministic extraction methods require assistance.

Impact

  • Reduced processing time from 30–60 minutes to under one minute
  • Supports multiple bureau formats
  • Validation-first architecture for reliable extraction
  • AI fallback only when required

Tech Stack

PythonPyMuPDFGemini APIOpenPyXLStreamlit


How I Build

  1. Observe the workflow.
  2. Identify recurring friction and operational/infomational bottleneck.
  3. Design a deterministic solution.
  4. Use AI only where reasoning adds value.
  5. Measure success by time saved, reliable system and better decisions.

Currently Building

  • CollectionIQ v2
  • Enterprise Underwriting Intelligence
  • AI Evaluation & Reliability
  • Workflow Automation for Lending Operations

Connect With Me

Email LinkedIn GitHub Resume

Building reliable systems that remove operational bottlenecks.

Pinned Loading

  1. CollectionIQ CollectionIQ Public

    An AI-powered loan portfolio dashboard built for Shriram Finance collection leaders. Upload a monthly LCC and the entire portfolio becomes instantly queryable in plain English, with automated risk …

    Python 1

  2. AI-Loan-analysis AI-Loan-analysis Public

    AI-assisted underwriting intelligence system for NBFC vehicle loan decisioning, combining deterministic risk validation with Gemini-powered qualitative analysis, document extraction, and RAG-based …

    Python 1

  3. AutoCAM AutoCAM Public

    Extracts structured loan account data from CRIF High Mark and TransUnion CIBIL PDFs and generates a formatted Excel file for credit analysts at Shriram Finance.

    Python 1

  4. Blog-writing-agent Blog-writing-agent Public

    Multi-agent AI content generation system using LangGraph with routing, retrieval, planning, parallel worker execution, and evidence-driven blog generation powered by Tavily and Gemini.

    Python 1

  5. MLOps--Vehicle-Insurance-Data-Pipeline MLOps--Vehicle-Insurance-Data-Pipeline Public

    Developed a fully modular and production-ready MLOps pipeline for predicting insurance policy responses, integrating CI/CD, containerization, and cloud services for robust deployment.

    Jupyter Notebook 1

  6. End-to-End-Azure-Data-Engineering-Pipeline-with-CICD End-to-End-Azure-Data-Engineering-Pipeline-with-CICD Public

    This is an end-to-end Azure-based Data Engineering pipeline following the Medallion Architecture (Bronze → Silver → Gold), built using tools like Azure Data Factory, Databricks, Delta Lake, Unity C…

    Jupyter Notebook 1