We can organize an interview with Aldin or any of our 25,000 available candidates within 48 hours. How would you like to proceed?
Schedule Interview NowMy name is Muhammad Umer B. and I have over 2 years of experience in the tech industry. I specialize in the following technologies: Artificial Intelligence, Retrieval Augmented Generation, LLM Prompt Engineering, OpenAI API, Whisper AI, etc.. I hold a degree in . Some of the notable projects I’ve worked on include: AI Lottie animation generator, WhisperX transcriber with recording and summarization, ChatGPT UI automation, Code Quality focused SWE Agent, Zillow Housing Data Scraper —Reliable, Detection-Resistant Web Crawler, etc.. I am based in Lahore, Pakistan. I've successfully completed 12 projects while developing at Softaims.
I'm committed to continuous learning, always striving to stay current with the latest industry trends and technical methodologies. My work is driven by a genuine passion for solving complex, real-world challenges through creative and highly effective solutions. Through close collaboration with cross-functional teams, I've consistently helped businesses optimize critical processes, significantly improve user experiences, and build robust, scalable systems designed to last.
My professional philosophy is truly holistic: the goal isn't just to execute a task, but to deeply understand the project's broader business context. I place a high priority on user-centered design, maintaining rigorous quality standards, and directly achieving business goals—ensuring the solutions I build are technically sound and perfectly aligned with the client's vision. This rigorous approach is a hallmark of the development standards at Softaims.
Ultimately, my focus is on delivering measurable impact. I aim to contribute to impactful projects that directly help organizations grow and thrive in today’s highly competitive landscape. I look forward to continuing to drive success for clients as a key professional at Softaims.
Main technologies
2 years
1 Year
1 Year
1 Year
Potentially possible
Confiz
This project builds an AI-powered infrastructure to generate South Park–styled vector animations using LLMs (Large Language Models) and modern animation tooling. The system allows users to input textual descriptions, dialogues, or storyboards, and produces JSON-based Lottie animations that can be embedded seamlessly in web and mobile applications. At its core, the project leverages LLMs to: Generate South Park–style character designs and motions, adhering to the show’s distinct cutout animation style.
In this project I had to build and deploy and API that uses whisperX for transcription, word segmentation and speaker detection on RunPod. On the frontend I had to build a python-tkinter GUI for recording and upload audio and getting it transcribed
This script automates interactions with the ChatGPT web interface using Selenium. It performs the following tasks: - Login: Automatically logs into the ChatGPT website with user credentials. - Message Sending: Sends custom prompts or messages to ChatGPT. - Response Collection: Waits for and retrieves ChatGPT's responses. - Data Storage: Saves the conversation (both prompts and responses) for later use. This tool can be used for tasks such as bulk prompt testing, dataset generation, or automated interaction workflows.
This project is an AI-powered Software Engineering (SWE) agent designed to autonomously test and debug full-stack MERN (MongoDB, Express, React, Node.js) applications. The agent integrates large language models (LLMs) with automated testing frameworks to identify, reproduce, and fix bugs across frontend and backend codebases. Resource-Constrained Execution: Optimized for efficiency, the agent completes its test-and-fix cycle within ~10 minutes and maintains a token usage budget of $0.30 per run.
Developed a robust web scraper to extract real estate listings from Zillow, including property details, pricing, location data, and listing metadata. Implemented stealth techniques such as undetected-chromedriver, proxy rotation, dynamic headers, and realistic interaction patterns to minimize detection risk. Optimized for large-scale data collection with error handling, adaptive retries, and structured output for seamless analysis.
in
2023-01-01-2027-01-01