TranslateX
An iOS-first real-time voice translation app for English and Japanese conversations.
Shipped personal appNauman Mustafa
AI systems engineer, former senior machine learning engineer, and indie builder.
I work on OCR, computer vision, LLM workflows, and software delivery with coding agents. This site is a small notebook for projects, field notes, and technical essays from that work.
Projects
Writing
Running a YouTube Channel on Autopilot
A 2-month YouTube automation experiment: scraping news, turning stories into videos, uploading them automatically, and learning hard lessons about niche, cost, and watch time.
Gaining 4 Years of Software Engineering Experience in 4 Months
AI changed my job from writing every line to directing parallel software systems. This is my field report from that shift.
From Vibe Coding to Compound Engineering
A software engineer journey from vibe coding to compound engineering, and what AI changes about architecture, intent, and code quality.
Lessons Learned Vibe Coding an iOS App from Scratch
Field notes from building an iOS app with AI coding tools, covering what worked, what failed, and how to ship faster with quality.
MLUI Mobile: Autify OCR vs. Google OCR
A benchmark of Autify OCR versus Google OCR on rendered mobile UI text, including methodology, accuracy metrics, and failure analysis.
Token Compression: Reducing Attention Waste?
An experiment on compressing multiple LLM tokens into one representation for faster decoding and longer effective context.
A quest for very long context: Part 1
Experiments on extending transformer context length, including training observations, tradeoffs, and lessons from long-context tuning.
Machine Learning Features in Autify for Mobile
How Autify for Mobile uses machine learning for visual regression testing, visual self-healing, and AI-powered app exploration.
Solving Automated App Navigation: A Use-case
A case study on automated mobile app navigation using behavior cloning and heatmap prediction for tap-location modeling.
Applying Modern Deep Learning in Autify
A practical guide to applying modern deep learning and pre-trained NLP models in production software and product workflows.
Getting the Most Out of Pre-trained Models
How to use pre-trained NLP models effectively for text generation and question answering, with practical examples and tradeoffs.
Recent Advancements in AI
A 2019 snapshot of major AI breakthroughs across text, image, audio, and video generation, with practical startup use cases.
This Icon Does Not Exist
Using GANs to generate unique icon designs, with model behavior examples and creative applications for design workflows.
Deploy Machine Learning Model
Step-by-step tutorial for packaging and deploying a machine learning app to Google Cloud Run with Docker and Cloud Shell.
Cloud Run
Overview of Google Cloud Run and how serverless containers can simplify deployment, scaling, and cost management for ML applications.
Deep Learning in Cloud
A cost-focused comparison of cloud GPU options for deep learning across AWS, Paperspace, Colab, and Google Cloud preemptible machines.