Full-stack AI engineer and co-founder of Codexyo, building LLM systems, RAG pipelines, voice agents and computer vision that actually hold up in production. I care about the stuff that matters once real users show up, like cost, latency and reliability, not just a demo that looks good on launch day.
>
Amir Aijaz is an AI engineer from Karachi, Pakistan, and co-founder of Codexyo, an AI engineering studio that builds production AI systems for businesses in North America, Europe and the Gulf. He holds a BS in Computer Science from the University of Karachi (2024).
Previously he was an AI Engineer at Viral Tech in Norway, where he built a multi-tenant agentic commerce chatbot engine, and he interned at the Smart City Lab of the National Centre of Artificial Intelligence at NED University, working on Urdu speech recognition and an Arabic voice assistant. His work covers large language model applications, retrieval-augmented generation, voice agents, computer vision and AI governance. He is the author of aigovkit, a Python SDK for AI governance and LLM observability published on PyPI, and governance-bench-v1, a public benchmark dataset on Hugging Face.
He also serves as fractional CTO for HAYA Trading Inc., a Canadian e-commerce company.
Co-founder of Codexyo, an AI engineering studio; I lead engineering and delivery. I build production AI systems for small and mid-sized businesses: legal-operations automation, voice agents for lead qualification, project-management platforms, inventory and forecasting tools, and quantitative analysis systems. I own architecture, cost budgets, testing and production launches end to end.
Own the digital business for HAYA Legacy (hayalegacy.com), a Canada-wide e-commerce brand: Shopify build and integrations, growth and marketing automation, analytics, and AI-assisted merchandising and customer-support tooling. Part-time, contract.
Built a production multi-tenant agentic commerce engine with Postgres row-level-security isolation, a WooCommerce adapter, a PII firewall and an owner dashboard, validated on a live 300+ product store. Added semantic retrieval with BGE-M3 embeddings on GPU and a cost-optimized LLM routing layer to keep per-conversation cost low at scale. Also built Knowlyst, a RAG system over web and video links, and benchmarked emerging LLMs on capability, latency and cost.
Built a self-hosted local LLM assistant for content & social media management; shipped text-to-image tools, automated HR screening and lead-generation agents; analyzed geospatial datasets for enterprise clients including CBL and EBM.
Built AI newsletter & blog generation tools with the Claude API, Flask and the YouTube Data API; automated team workflows and deployed scalable applications on AWS.
Developed Python scripts measuring 2D object distances in warehouse environments and applied open-source depth-estimation models to real-time CCTV feeds.
Built an Arabic-language medical voice assistant for Sahl AI - dataset prep, fine-tuning and integration - and ran comparative analysis of Wav2Vec vs. Google Speech for Urdu speech-to-text.

LLM observability & safety platform: model registry with risk classification, full audit logging, automated PII & toxicity detection, and one-click NIST AI RMF compliance reports. Published Python SDK on PyPI.
→
Production outbound and inbound voice agent for automated phone qualification and warm transfer. Multi-tenant, TCPA-compliant and backed by 586 hermetic tests, with a concurrency-safe dispatcher. Private client build.
→
RAG assistant that lets legal teams query large PDFs in natural language with cited answers. Supports Gemini, OpenAI and local Ollama backends.
→
Offline backtesting harness validating trading strategies over ~9 years of BTC, ETH & SOL data, net of realistic fees and slippage - with strict no-look-ahead discipline and a go/no-go report. Private client build.
→
Multimodal medical assistant that analyzes medical images, answers health questions, and supports voice interaction using LLMs and computer vision.
→
CrewAI multi-agent system that researches the market, plans content, generates visuals and writes captions to automate Instagram content end to end.
→20 projects · filter by domain
University of Karachi · 2021 — 2024
Final year project: SignVision, a real-time Urdu sign-language recognition system. Coursework in AI, NLP, statistics & data mining.
Amir Aijaz is an AI engineer from Karachi, Pakistan, and co-founder of Codexyo, an AI engineering studio. He builds production LLM systems, RAG pipelines, voice agents and computer vision, and is the author of the aigovkit Python SDK and the governance-bench-v1 dataset.
Codexyo is an AI engineering studio co-founded by Amir Aijaz that designs and ships production LLM systems, voice agents, RAG pipelines and automation for small and mid-sized businesses.
aigovkit is an open-source Python SDK by Amir Aijaz for AI governance and LLM observability, providing a model registry, audit logging, detection hooks and compliance reporting. It is published on PyPI.