Currently building document and voice AI for enterprise teams

Praveen Kumar

Principal AI Engineer & Solution Architect

Six years of it. Mostly speech AI

I take AI systems from the first rough prototype to the version that survives real traffic, real documents and real users. Everything I learn on the way ends up here, written down properly.

See the work About Resume GitHub

Selected work

Three I'd show you first

Thirteen projects live in the archive. These three are the ones that taught me the most about shipping AI that other people depend on.

Document AI FastAPI PostgreSQL Kubernetes

Docuvera — Loss360

Multi-tenant SaaS that turns insurance loss-run PDFs and scans into structured claims data. A custom OCR engine feeds domain-tuned LLMs, with schema-per-tenant isolation in PostgreSQL so no client's data can leak into another's.

Lead engineer, team of 8 92% extraction accuracy 10+ tenants live Read the write-up

MoM AI meeting minutes application homepage

LLM & RAG Flask Celery Redis Docker

MoM AI — Minutes of Meeting

Drop in a recording, get back minutes. FFmpeg normalizes the audio, a Celery worker routes it to one of four speech-to-text providers, and an LLM returns the summary, the decisions and the action items. Both providers swap at runtime.

4 STT providers behind one factory Open source Read the write-up

LLM & RAG PyTorch FAISS DistilBERT

Context Search Engine

Semantic search over your own documents. PDFs, DOCX and text files are chunked with overlap, embedded with DistilBERT and indexed in FAISS. Chunk size, overlap, model and top-k are all knobs, because retrieval quality is an empirical question.

Sub-200ms queries Runs entirely offline Read the write-up

Browse all 13 projects

The short version

Models are the easy part

The hard part is everything around them: the queue that retries, the tenant boundary that holds, the GPU bill that doesn't spiral, the transcript a human can actually correct. That's the work I've spent six years getting good at — speech intelligence, document processing and LLM automation, mostly for enterprise teams who need it to hold up on a Monday morning.

Years building AI systems

10+

Production AI platforms

50+

Models deployed

Projects written up here

The longer version

Say hello

Got something hard to build?

I like problems where the obvious approach doesn't work yet. Email is fastest, but any of these reach me.

Email LinkedIn GitHub Twitter Resume