Solutions Engineer · Production LLM Applications
Recently won a $1.3M proposal at a global insurance carrier on a visual + text extraction pipeline. Open to Solutions Architect, Forward Deployed Engineer, and Solutions Engineer roles at LLM-first companies. Based in India, open to relocation anywhere in the world.
A quick intro
I turn enterprise AI proofs-of-concept into production systems.
Four-plus years as a Solutions Engineer for Fortune-100 insurance and Tier-1 banking customers. I own the technical motion end to end, from the first pre-sales POC through deployment, and I build for reuse, so the systems I ship keep working long after handoff.
Rahul Nanwani
global insurance carrier
Led a competitive technical evaluation to automate extraction from Japanese handwritten medical certificates. The pipeline handles era-based date conversion (Japanese imperial calendar to Gregorian), hanko stamp recognition, signatures, and circled checkbox selections that the text-only baseline could not address. Won the evaluation; the customer is moving toward production rollout.
$1.3M TCV / $433K ARR proposal wonFortune-100 U.S. life insurer
Own the post-sales technical delivery of an 80-field LLM extraction workflow handling around 30,000 pages per year. It consolidates 40-50 page claims documents into structured outputs and analyst-ready summaries; I co-design the schemas with the customer business team and ship Python accuracy-validation utilities that compare outputs against ground truth.
80 fields, ~30k pages/year, in productionTier-1 commercial bank
Took over as the customer-side technical advisor across five-plus production LLM solutions after a team transition. The primary document-processing pipeline now saves 31 FTEs (around 52,000 hours per year), with classification accuracy lifted from 45% to 80% and extraction +75%. Accuracy lifts also shipped across four more lines of business, including trade finance, cheque processing, and debt collection.
31 FTEs (~52,000 hrs/yr) savedTier-1 UK insurer
Shipped a postal claims-intake solution to UAT completion at 96.2% field automation accuracy across 70 fields and four LLM-based models. Designed the solution architecture, trained a new engineer mid-project, and recovered an aggressive timeline after a parallel production incident.
96.2% accuracy across 70 fieldsA complete library for blackjack rounds: multi-player tables, configurable multi-deck shoes, the full action set (hit, stand, double-down, split, surrender), and configurable dealer rules. Versioned releases on PyPI with a test suite, CI, and documentation on Read the Docs. Latest release: v5.0.0 (March 2026).
I define how success is measured before I build the thing that has to meet it. That is why the systems I ship keep working after I hand them off.
Apr 2024 – present
Solutions Engineer II
Production LLM applications for Fortune-100 insurance and banking, from pre-sales POC through deployment.
Oct 2022 – Mar 2024
Solutions Engineer I
Shipped claims-indexing and extraction solutions to production across insurance and banking.
Jul 2022 – Oct 2022
Data Operations Lead
Led a team of associates and cut project ramp time by 3+ weeks with new data-preparation strategies.
Aug 2021 – Jun 2022
Data Operations Associate
Contributed to 10+ client use cases and 5+ pre-sales POCs across banking, insurance, and mortgage.
2024 – 2025
M.Sc. Machine Learning & AI
Liverpool John Moores University, UK
Thesis: Explainable AI for Image Classification.
2023 – 2024
Executive PGP, Machine Learning & AI
IIIT Bangalore, India
2017 – 2021
B.Tech, Computer Science & Engineering
MIT ADT University, India