I will build ai voice agent, ai receptionist, ai calling agent using vapi retell

A
ajwa129
A
ajwa129
Choudhry S

About this gig

Your business misses calls every day. Each one is a lost booking or a lost lead. I build AI voice agents that answer every call 24/7, talk naturally with callers, and book appointments directly into your calendar.


I have built production voice agents for real businesses, including an AI receptionist for an accounting firm handling 3 appointment types with reschedule and cancel flows, and a booking agent for a dental clinic. These systems take live calls today.


What I build for you:

  • AI voice agent / AI receptionist on Retell AI or Vapi
  • Inbound call answering with natural conversation
  • Appointment booking with Cal.com, Calendly, or GoHighLevel calendar integration
  • Reschedule and cancel handling
  • Lead qualification and ai cold calling flows
  • SMS confirmations and CRM sync via n8n automation
  • Premium voices with ElevenLabs


Why me instead of a template seller: I am an infrastructure engineer. I build the full pipeline behind the agent, including webhooks, APIs, and error handling, so your agent does not break when a caller says something unexpected.


Note: Retell/Vapi/Twilio usage costs are billed on your own accounts.

Message me before ordering and I will map your call flow for free.

Get to know Choudhry S

Choudhry S

AI Platform Engineer, vLLM, GPU Kubernetes, DevOps, Cloud and Security

  • FromPakistan
  • Member sinceAug 2019
  • Languages

    Urdu, English
I build and run GPU and LLM infrastructure, on-prem and in the cloud. I wrote IaC for GPU cluster orchestration on KAUST Shaheen III, the Middle East's #1 supercomputer (2,800 NVIDIA GH200s). Real results: vLLM latency cut from 3.2s to 800ms, monthly cloud bill dropped from $10K to $4K, LLMs served to 1,000+ concurrent users on bare-metal Kubernetes with zero downtime for 12 months. Stack: vLLM, Triton, GPU Kubernetes (bare-metal and GKE/EKS/AKS), Terraform, Ansible, Ray, Kubeflow, RAG, voice agents. I run a dual RTX Pro 6000 server at home. On-prem GPU work is my daily reality.

My Portfolio