PRANAVPANCHAL
I engineer production-grade data and AI systems that transform complex enterprise information into scalable intelligence.
From raw data → pipelines → intelligence → AI products.
Hover a node to inspect its role in the system.
I don't just analyze data.
I engineer the systems behind it.
Data infrastructure. AI platforms. Intelligent automation. Production systems.
Years Building Data & AI Systems
Manual Work Reduced Through Automation
Faster Access to Actionable Insights
Faster Analytical Workflows in AI Projects
Engineer. Architect. Automate.
location Nashville, TN
focus Data platforms · GenAI/RAG · Cloud · Automation
status available
I'm Pranav Panchal, an AI & Data Engineer currently working as an Operations Development Engineer at Institutional Life (ILS), where I architect the organization-wide data platform and build the applications and AI systems that run on top of it.
My work spans the complete data and delivery lifecycle — from ingestion, transformation and warehousing to semantic retrieval, document intelligence and generative AI — all the way through to the CI/CD pipelines, containerized deployments and infrastructure-as-code that ship it safely to production.
I enjoy solving the difficult engineering problem behind AI: getting the right data, in the right structure, to the right model — reliably and at scale — and then automating the pipelines, observability and infrastructure that keep it running.
I bridge technical architecture and business requirements to build systems that don't stop at prototypes — they solve real operational problems.
The map of what I engineer.
One center of gravity — data and AI engineering — with the disciplines that make production systems actually work.
AI + DATA
ENGINEERING
7 connected disciplines · 45+ technologies
- ETL / ELT
- Data Pipelines
- Data Modeling
- Data Warehousing
- Data Lakes
- Event-driven Processing
- Data Quality
Selected Systems I've Built
Real engineering. Real architecture. Real outcomes.
What I Actually Build
Sources → Lake → Warehouse → Intelligence
Data Platforms
I design scalable cloud data architectures that turn fragmented operational information into reliable analytical systems.
Documents → Embeddings → Retrieval → LLM
AI Knowledge Systems
I build RAG architectures that allow organizations to query complex proprietary knowledge safely and accurately.
PDF → OCR → Classification → Structured Data
Document Intelligence
I engineer pipelines that transform inconsistent PDFs, scans, tables and records into usable structured information.
Manual Workflow → Intelligent Pipeline
Enterprise Automation
I automate repetitive operational processes using cloud infrastructure, Python and AI.
Model → API → UX → Business Outcome
AI Products
I build usable applications around models — not just notebooks.
Code → CI/CD → Containers → Production
DevOps & Infrastructure
I build automated pipelines, containerized deployments and monitored infrastructure that ship systems safely and reliably — part of the platform work behind my role at Institutional Life.
Data → Intelligence
My Engineering Stack
Architecture Lab
How I think about intelligent systems.
Data Sources
Contracts first — know the shape and cadence before ingesting.
How I Engineer
Start with the business problem.
Technology is useful only when it changes an outcome.
Design the data foundation.
AI quality is constrained by the quality and accessibility of its data.
Engineer for reliability.
Production systems need observability, security, validation and recoverability.
Use AI where AI actually helps.
Not every problem needs an LLM.
Measure the result.
Automation should save time, improve quality or unlock capabilities that weren't previously possible.
Progression
Roles described by the systems built and the problems solved.
Insured, policy, medical, underwriting, longevity and valuation data scattered across disconnected systems, with underwriting knowledge locked inside thousands of unstructured insurance documents and no unified way to query any of it.
An organization-wide database and AWS data platform (Redshift, S3, Terraform) unifying every core data domain, paired with a full web application and LLM-powered knowledge base — a RAG pipeline with a document classification model spanning 7 insurance document categories, insured identity validation, category/file/date-aware filtering and citation checks for traceable, natural-language search across organizational documents. Also delivered 6 production ETL pipelines and Lambda-based incremental loads, plus underwriting tools integrating ExamOne and Digital Owl data with internal scoring, overrides and cross-table deduplication.
Improved efficiency by 90% in targeted business processes; unified data platform now powers applications, analytics and a natural-language knowledge base across the organization.
Education & Certifications
Master of Science — Business Analytics
University of Texas at Dallas
Bachelor of Technology — Information Technology
Indus University
Have a difficult data or AI problem?
Let's build something intelligent.