Client work and own products
I build production AI systems for enterprises, and ship my own products solo. I translate what breaks in AI into plain English for the people paying for it.
Work delivered for teams at Coca-Cola, and enterprise clients in global logistics, US healthcare, finance and document management.
Problem, what I built, outcome, stack. Every number is from the CV. No logos. No testimonials.
Forward Deployed Engineer · Feb 2026 to present
Problem
Teams were manually searching more than 50,000 unstructured documents to answer routine questions.
What I built
Architected and deployed a production multi-agent Retrieval-Augmented Generation pipeline over the full corpus.
Outcome
Cut information-lookup time by approximately 99% versus manual review.
Stack
Python, FastAPI, LangChain, OpenAI API, Claude API, Pinecone, PostgreSQL, Docker
Global logistics enterprise
Problem
Accounts-payable invoices were processed by hand, with duplicate-payment risk and no audit trail.
What I built
End-to-end AP pipeline: document-AI invoice ingestion, multi-tier reference resolution, rate-card auditing, and automated posting into an on-premises ERP. Twelve coordinated agents. Idempotency keys throughout.
Outcome
800-line invoices processed in under 2 minutes. Full audit trails. Duplicate-payment risk eliminated.
Stack
Python, FastAPI, LangChain, document AI, REST APIs, PostgreSQL, on-prem ERP integration
US healthcare provider
Problem
Referrals required manual work across an EMR, an insurance portal and cloud fax. ~30 minutes each.
What I built
An agentic system spanning all three surfaces, with HIPAA-conscious in-memory PHI handling and a human-in-the-loop exception queue.
Outcome
Per-referral processing cut from ~30 minutes to under 2 minutes, a 93%+ reduction.
Stack
Python, FastAPI, LangChain, EMR + portal + fax integrations
Separate from client work. Shipped solo, or as founding engineer.
Hindi + English
Kahani Ghar
Bedtime stories. On Google Play. Paying subscribers.
Featured product
A bedtime-stories app for kids, in Hindi and English. I built the Android app, the backend and the content pipeline end to end, and launched it on Google Play.
Paying subscribers · shipped solo
Live on Google Play
Google Play →Own build
A consumer LLM app I built and launched independently. Hierarchical memory: raw chat to per-session summaries to a summary-of-summaries in the system prompt. No vector database, no embeddings.
110+ users in the first 5 days
Live
riya-ai.site →Own build
Automated ad-ops platform optimising Facebook and Instagram campaigns.
300+ conversions at $10 CPA, campaign setup time cut ~40%
Built at The App Company
