Hey, I’m Qasim
Site Reliability Engineer and Cloud Infrastructure Specialist with 10+ years of experience building and maintaining production systems at scale. Based in the Greater Toronto Area, I’ve architected cloud infrastructure serving millions of requests daily and led DevOps transformations for teams across multiple industries.
My current focus is the intersection of reliability engineering and AI — building intelligent automation systems that monitor, heal, and optimize infrastructure without human intervention. agentbus.sh is where I share practical guides on working with AI: from large language models and prompt engineering to deploying ML pipelines and building autonomous agents.
Why agentbus
AI is moving fast and the documentation can’t keep up. Most guides are either too theoretical or outdated within weeks. agentbus.sh is a collection of practical AI guides covering the “how to” questions developers search for every day — LLMs, agents, computer vision, MLOps, and more.
Every guide follows a simple pattern:
Problem → Solution → Explanation.
No fluff, no filler, no “before we begin, let me tell you about my journey.” Just working code examples and real troubleshooting tips.
Expertise & Credentials
Certifications:
- AWS Certified Solutions Architect – Professional
- AWS Certified DevOps Engineer – Professional
- AWS Certified Developer – Associate
- AWS Certified SysOps Administrator – Associate
AI & ML Expertise:
- LLMs & Agents — Claude API, OpenAI, prompt engineering, tool use, multi-agent systems, RAG pipelines
- MLOps — Model serving (vLLM, TGI), training pipelines, monitoring, A/B testing
- Computer Vision — Object detection, image classification, video analysis, YOLO, OpenCV
- Infrastructure — GPU clusters, distributed training, cloud ML (AWS SageMaker, GCP Vertex AI)
- Programming — Python (10+ years), Go (6+ years), TypeScript/Node.js, Rust