Home/Expertise

LLMOps and self-hosted inference

Self-hosted inference with Ollama, GPU cost control, and the deployment path from a local model to a containerized service. Written from shipped work by Muhammad Huzaifa Shahbaz, AI Systems Engineer at Digital Dividend Global.

What I build

  • Self-hosted LLM and speech services (Ollama, Whisper) for products that should not send every request to a hosted API.
  • Quantized PyTorch models aimed at IoT hardware, where a cloud round-trip is the wrong dependency.
  • The surrounding ops: Docker, Kubernetes, queues, and CI so a model is a service with logs, not a notebook.

Architecture

  • At Lenaar, Ollama served self-hosted LLMs and Whisper, with GPU use tuned so inference was cheaper to run.
  • ViralMe Studio runs AI inference beside a Remotion render pipeline: FastAPI and Python for model calls, Node workers, RabbitMQ for jobs, Kubernetes on Azure.
  • At Digital Dividend, quantized LLMs (PyTorch, Ollama) were prototyped for on-device IoT inference. FunctionGemma is in evaluation for agent-style tool calls on that hardware.
  • A public workshop for Karachi.AI walked the same arc: local inference, RAG, fine-tuning on Gemma, then deployment.

Production constraints

  • Hosted APIs are simpler until cost, data residency, or offline hardware rules them out. Self-hosting trades that bill for GPU scheduling and model upgrades.
  • ViralMe's published target was 99.5% uptime for the editing platform, with render jobs queued rather than run inside the request.
  • A quantized model that fits on a device is not the same model that won the demo. The prototype work is explicitly an evaluation, including FunctionGemma.

Stack

Ollama · PyTorch · Whisper · Docker · Kubernetes · RabbitMQ · Azure · FastAPI

Tradeoffs

  • Ollama is a fast way to run a known model. It is not a substitute for evaluation, canary deploys, or a queue when inference is slower than the user will wait.
  • On-device quantization wins on privacy and connectivity and loses on quality versus the full model used in the cloud product.

Projects

  • ViralMe Studio — Ollama inference next to a queued Remotion render pipeline.

External verification

Questions

Has he run self-hosted models in production systems?

Yes. Ollama served LLMs and Whisper at Lenaar, and Ollama is part of the ViralMe Studio inference path. Quantized on-device models for IoT are prototypes under evaluation.

Where is the public record of the LLMOps teaching?

The May 2026 Karachi.AI workshop on local LLMs, RAG, and Gemma fine-tuning is listed on the speaking page, with slides linked from that entry.

Other expertise

I love working in Software Dev, Artificial Intelligence & DevOps

M. Huzaifa Shahbaz

All rights are reserved or permitted. ©