Let's talk
Available for project
(GMT+5:30) SUNRAISE-AI.IN

Conversational
AI, built
quietly & local.

About
NameMuddana Bala Venkata Raghavendra Chowdary
RoleGenesys Consultant · AI Engineer
Experience4 years 4 months

A solo studio of one — building chatbots, voicebots & retrieval systems for banks, hotels and contact centres. Seven services running right now on one local machine, behind one nginx.

Scroll See latest work
About

I combine four years of conversational‑AI work to build meaningful, story‑driven systems — for businesses that actually need them.

No managed cloud. Every service in this portfolio runs on one host I administer myself, behind a single nginx gateway. Cheaper to run, quicker to change.

No vendors. Local LLM inference for the parts that matter, with Claude & Gemini routed through Nomotron — my own OpenAI-compatible wrapper.

One team — one human. From Genesys flow to voice pipeline to retrieval index, I write & ship every layer. Fewer handoffs, faster iteration.

Why me

Numbers don't lie.

Four years building conversational systems end-to-end. Every line — flow logic, LLM glue, voice pipeline, retrieval index — written by one person, shipped to production.

07+ Live services running on sunraise-ai.in
04y Years building conversational AI in production
100% Local inference — no third-party model calls by default
<1s Voice turn-taking latency on a single host
Process

How I work.

Four short steps from a conversation about your problem to a service running on your domain. Async, transparent, no hand-offs.

Step 01.

Discovery .

30-minute call. Your goal, your constraints, the existing CCaaS stack & where conversational AI actually moves the needle.

~ 1 day
Step 02.

Kickoff .

Scope, milestones & a shared repo. I spin up the local stack, wire the model gateway, and we start in days, not months.

~ 1 week
Step 03.

Ship & refine .

Weekly demos against real conversations. Iterate the prompts, flow, retrieval & voice pipeline until the metrics actually move.

~ 4 weeks
Step 04.

Operate .

Go-live on your domain or mine. Ongoing tuning, observability, model upgrades — the service grows with the conversation volume.

ongoing
Stack

Tools of trade.

A small, opinionated set of tools that fits on one machine — chosen because I can read every line of every layer when something breaks.

I work in Python·Genesys Cloud— and lately —LLM fine‑tuning·QLoRA·agentic systems·retrieval.

Infrastructure

Gatewaysunraise-ai.inTLS · nginx
RuntimePython · Node · Uvicornlong-lived
StoresPostgres · Redis · Qdrantlocal
HostingG-drive local stacksingle host
VoiceWebRTC streamingsub-1s

Languages & Models

PrimaryPython · TypeScriptdaily
ServerC# · ASP.NET · Nodelegacy
Front-endReact · HTML · CSSoften
ModelsLocal LLM · Claude · Geminirouter'd
CloudAzure · GCPwhen needed
Let's work together

Have a project
in mind?

Drop a line. I reply within 24 hours and the first call is free. If we don't fit, I'll point you toward someone who does.

Get in touch