AI Infrastructure Engineer

Rashesh Patel

6 projects across AI infrastructure, OpenStack private cloud, and VoIP telephony —
from GPU clusters and LLM pipelines to SIP agents and production SLOs.

Ahmedabad, India · +91 96243 08060
01

Projects

01 Voice Agentic AI Platform Real-time voice assistant on Kubernetes — Browser mic → Whisper STT → Mistral 7B ReAct agent (weather, search, calc tools) → Edge TTS. GitOps with ArgoCD + vLLM GPU serving. KubernetesArgoCDvLLM
02 LLM Fine-Tuning Platform Self-service LoRA fine-tuning — upload dataset, get model auto-evaluated and promoted to MLflow. 5-step Argo Workflow DAG: ingest → preprocess → KubeRay train → eval → register. KubeRayMLflowArgo
03 AI Platform Ops Production operations layer for Projects 1 & 2 — custom kopf operator auto-deploys MLflow models, KEDA scales Ray workers to zero, Argo Rollouts canary gates, OTel traces, SLO burn-rate alerts. kopfKEDAOTel
04 HA OpenStack Deployment Production private cloud with Kolla-Ansible — 3-node HA controller cluster (Keepalived VIP + HAProxy + Galera + RabbitMQ), 4 compute nodes, 3-node Ceph storage. Automated deploy & health scripts. OpenStackCephKolla
05 GPU Cloud for AI/ML GPU-enabled OpenStack — NVIDIA A100/T4 PCI passthrough via vfio-pci, Ironic bare-metal provisioning, VLAN 200 training network (MTU 9000 for NCCL), Heat templates for self-service CUDA instances. IronicVFIOHeat
06 AI Phone Agent SIP phone calls handled by an AI agent — FreeSWITCH mod_audio_stream pipes RTP to Python bridge in real time, WebRTC VAD detects speech end, same Whisper→Mistral→TTS pipeline answers the call. FreeSWITCHSIPVAD

Voice Agentic AI Platform

Real-time voice assistant on Kubernetes. Browser microphone to audio response in under 4 seconds — Whisper transcribes speech, Mistral reasons and calls tools, Edge TTS speaks the answer back.

Browser mic Whisper STT Mistral 7B ReAct Edge TTS Audio
Python FastAPI Kubernetes ArgoCD vLLM Helm GPU

LLM Fine-Tuning & Evaluation Platform

Self-service training platform — upload a dataset, get a fine-tuned model auto-evaluated and registered in MLflow. A 5-step Argo Workflow DAG handles preprocessing, distributed training, evaluation, and promotion.

Dataset MinIO KubeRay LoRA MLflow Eval Staging Production
Python KubeRay HuggingFace PEFT MLflow Argo Workflows MinIO

AI Platform Ops — Production Operations Layer

Closes all production gaps in Projects 1 and 2. Five components that separate a demo from a system that runs at 3 AM without anyone watching.

Custom K8s Operator MLflow → K8s auto-deploy in 30s via kopf @kopf.daemon
OTel + Tempo STT / LLM / TTS waterfall traces — blame the right service in 30s
KEDA Scale-to-Zero Ray workers idle 16h/day → ~60% GPU cost savings
Canary Rollouts 10% → 50% → 100% with Prometheus analysis gates, auto-abort
SLO Alerts Google SRE burn rate formula — fast burn 14×/1h, slow burn 6×/6h
kopf OpenTelemetry Grafana Tempo KEDA Argo Rollouts Prometheus

Production HA OpenStack — Kolla-Ansible

Full private cloud deployment: 3-node HA controller cluster (Keepalived VIP + HAProxy + MariaDB Galera + RabbitMQ), 4 compute nodes, 3-node Ceph storage backend. Automated deploy scripts with pre-flight checks and post-deploy resource provisioning.

Bootstrap Prechecks Deploy Post-Deploy Horizon
OpenStack 2024.1 Kolla-Ansible Ceph HAProxy Keepalived Neutron OVS Bash

GPU Cloud for AI/ML — OpenStack + Ironic

Extends OpenStack for self-service GPU compute. NVIDIA A100/T4 PCI passthrough via vfio-pci, Ironic bare-metal for workloads that can't tolerate hypervisor overhead, VLAN 200 training network with MTU 9000 for NCCL distributed training, and Heat templates for one-command GPU instance provisioning with CUDA + PyTorch.

PCI Passthrough NVIDIA A100 & T4 via vfio-pci — full GPU memory, no hypervisor overhead
Ironic Bare Metal iPXE boot provisioning for large-model training nodes
NCCL Training Net VLAN 200, MTU 9000 jumbo frames — optimised for AllReduce collective ops
Heat Templates One command: GPU instance + CUDA 12.4 + PyTorch cloud-init
OpenStack Ironic NVIDIA GPU VFIO Heat Ansible CUDA

AI Phone Agent — FreeSWITCH + LLM

Bridges a SIP telephone network to the Kubernetes AI voice pipeline. A caller dials in, FreeSWITCH handles SIP/RTP, and mod_audio_stream streams audio in real time to a Python bridge — through the same Whisper STT → Mistral ReAct → TTS pipeline. The AI answers phone calls.

SIP Caller FreeSWITCH Whisper STT Mistral ReAct TTS → Caller
FreeSWITCH mod_audio_stream SIP / RTP WebRTC VAD Kubernetes Python FastAPI
02

Skills

Kubernetes & GitOps
Kubernetes ArgoCD Helm KEDA Argo Rollouts Argo Workflows Custom Operators
Observability
OpenTelemetry Grafana Prometheus Grafana Tempo SLO Engineering
ML Infrastructure
KubeRay vLLM HuggingFace PEFT MLflow MinIO GPU Workloads
Telephony & VoIP
FreeSWITCH Asterisk SIP / RTP mod_audio_stream WebRTC VAD ESL
OpenStack & Cloud Infra
OpenStack Kolla-Ansible Ceph Ironic Neutron GPU Passthrough Heat
Languages & Tools
Python FastAPI Bash Docker Git
03

Connect

Let's build something.

// open to AI infrastructure roles  ·  Ahmedabad, India