Hammad Wakeel

AI Engineer

BitCoderLabs Pvt Ltd • Full time

Jul 2025 - Jan 2026 • 6 mos

Project Focus: Scalable AI Backends & Automated Marketing Intelligence During my tenure at BitCoderLabs, I served as a core AI Engineer Intern, focusing on bridging the gap between high-performance web architecture and Generative AI. My primary responsibility was the development and optimization of scalable backends designed to support high-traffic AI-driven applications. Key Technical Contributions: Architecting FastAPI Ecosystems: I engineered robust, asynchronous backends using FastAPI and Python. My focus was on reducing latency for LLM API calls, ensuring that users received near-instantaneous responses even when processing complex prompts. Meta Ad Persona Generation: I led the development of a custom AI module that revolutionized the way marketing teams approach audience targeting. By leveraging GPT-4o and advanced prompt engineering, I built a system that analyzes market trends to generate high-conversion buyer personas automatically. This reduced manual research time by over 70%. Secure Infrastructure with Supabase: I managed the integration of Supabase for secure user authentication and real-time database management. I specifically focused on row-level security (RLS) and efficient data fetching to ensure enterprise-grade security for user data. Financial Integration: I implemented the Moyasar payment gateway for a seamless SaaS checkout experience. This involved handling secure webhooks, managing subscription lifecycles, and ensuring full compliance with digital payment standards. Impact & Results: By the end of my internship, the systems I built were capable of handling thousands of concurrent requests without degradation. My persona generation tool was adopted as a core feature of the company's internal marketing suite, providing a direct boost to their digital ad campaign performance.

AI Engineer

EnDevSols (Pvt.) Ltd • Full time

Apr 2024 - Jul 2024 • 3 mos

Project Focus: Agentic RAG Systems & Content Automation Pipelines At EnDevSols, I was tasked with pushing the boundaries of conversational AI and automated content generation. As an AI Engineer Intern, I worked at the cutting edge of Retrieval-Augmented Generation (RAG), transforming static data into interactive, intelligent agents. Key Technical Contributions: Real-Time Sports RAG Chatbot: I architected a high-performance sports chatbot using LangChain and Vector Databases. The unique challenge was integrating real-time web search APIs to ensure the bot could discuss live scores and breaking news alongside historical data. This system achieved a 40% increase in response accuracy compared to standard LLM benchmarks. Multi-Modal Content Pipeline: I built an end-to-end automation system that integrated GPT-4 for text generation and DALL-E 3 for image creation. This pipeline was designed for social media managers, allowing them to turn a single topic into a full week’s worth of visual and written content in seconds. Efficiency Optimization: My automation tools resulted in a 90% reduction in content creation time. What previously took a team of three hours to research and design could now be generated in under 10 minutes, maintaining a high level of brand consistency and SEO optimization. LangGraph Implementation: I experimented with LangGraph to build "Agentic" workflows, allowing AI agents to self-correct and verify facts before presenting them to the user, significantly reducing hallucinations. Professional Excellence: Throughout this role, I applied the same analytical rigor that earned me two Bronze Medals and a 3.78 CGPA during my BS in AI. I contributed to the company’s GenAI roadmap, helping them identify high-impact areas for future automation and RAG-based products.