A research-driven engineer at the intersection of Human-Computer Interaction (HCI) and AI. Experienced in fine-tuning LLMs (35% hallucination reduction) and building end-to-end products, from campus-wide logistics to interactive educational platforms. Passionate about creating human-centric AI systems that solve real-world social challenges through thoughtful design and rigorous engineering.
Lahore, Pakistan
Experience
Jan 2025 – Jan 2025
WORK
Software Engineer Intern
10Pearls LLC
Focused on the development and optimization of AI-driven therapy chatbots using Large Language Models and modern web technologies.
•Fine-tuned 4+ Large Language Models (LLMs) on a therapy-specific dataset using PyTorch and Hugging Face
•Developed a minimalistic internal web interface using React and TypeScript to facilitate expert testing and chat logging
•Implemented an automated evaluation pipeline using DeepEval to benchmark inference latency and accuracy
•Managed iterative fine-tuning cycles with continuous hyperparameter optimization and automated evaluation feedback loops.
Key Achievements
→Reduced hallucination rate by 35% through targeted fine-tuning on therapy-specific datasets.
→Optimized model verbosity and response length to align with expert recommendations, significantly reducing irrelevant content generation.
→Improved response reliability by implementing advanced context-retention strategies for nuanced conversational flows.
→Established benchmarking for ROUGE scores and hallucination frequency using DeepEval.
→Collaborated with 4 domain experts to utilize curated longitudinal therapy datasets, ensuring high-fidelity context retention.
→Iteratively optimized hyperparameters through rigorous testing cycles, using DeepEval metrics to drive performance gains.
→Reduced hallucination rate by approximately 35%
→Improved response reliability through targeted fine-tuning
→Established benchmarking for ROUGE scores and hallucination frequency
PyTorchHugging FaceReactTypeScriptDeepEval
Jan 2023 – Jan 2023
INTERNSHIP
Web Development Intern
CallConnect BPO
Contributed to frontend UI refinement and backend integration for product discoverability and user retention.
•Developed and refined frontend UI components with React, HTML, CSS, and JavaScript
•Implemented responsive design improvements using CSS Grid and optimized navigation flows
•Integrated frontend features with backend workflows using Node.js and MongoDB
Key Achievements
→Improved 50+ product pages for better discoverability and usability
→Reduced user drop-off by approximately 20%
→Supported multi-role functionality and sales tracking integration
ReactHTMLCSSJavaScriptCSS GridNode.jsMongoDB
Project Portfolio
PERSONAL
Present
3D Visualization from 2D Images
Implemented a 3D reconstruction pipeline from 2D image batches using Structure from Motion (SfM) and pose estimation techniques.
PythonOpenCVStructure from Motion (SfM)Computer Vision
PERSONAL
Present
Gender Bias Education Platform (FYP)
A research-driven project at the intersection of Human-Computer Interaction (HCI) and AI. Built a playful interactive world-building platform for pre-teens to learn about gender biases. Users design a 'utopian world' by choosing locations and assigning character roles. Features a polite AI chatbot that acts as a gentle guide, asking thoughtful questions to encourage exploration of unbiased choices and praising counter-stereotypical decisions to reinforce learning without shaming. Currently exploring an Android version to increase accessibility.
HCIAILLMPythonReactUI/UX Design
PERSONAL
Present
LUMS Campus Delivery Platform
Full-Stack Developer (Backend Focus)
A localized food delivery platform for the LUMS campus, mimicking Foodpanda with campus-specific logistics. Implemented Google Maps API for route optimization and used WebSockets for tracking infrastructure. Developed the backend to handle campus-specific delivery zones and coordinate mapping.