Usman Haider
AI/ML & Data Solutions Engineer
New to Contra
Usman is ready for their next project!
Retail Knowledge Graph
In this project, we built a semantic knowledge graph tailored to the retail industry. The pipeline involved developing AI agents to transform heterogeneous data into standardized formats. Ontologies were created to represent domain knowledge accurately. Using Gemini models and LangChain, user queries were converted into Cypher queries to retrieve insights from a Neo4j database. We utilized an MCP server for orchestration and LangSmith for secure login and audit trails. This system enhances complex data exploration for non-technical users.
2
2
79
Student Medical Chatbot
Built a chatbot to assist MBBS students in navigating medical literature. Leveraged Llama Index and fine-tuned language models to ensure accuracy. Embeddings were stored in OpenSearch, hosted on AWS. The Django backend included secure authentication and session management for a robust user experience.
0
51
Prompt Engineering Mini-Academy is a digital learning product built using Kajabi. It helps users learn how to write better AI prompts and use AI tools for daily tasks such as writing, research, summarization, and productivity.
The problem it solves is that many people use AI tools without a proper structure, which leads to weak or generic results. This product gives users a clear learning path, practical prompt templates, and workflow examples to improve the quality of their AI outputs.
I used Kajabi to create the landing page, email capture form, downloadable prompt resource, product offer, checkout page, and course structure. A sample video is attached to demonstrate the product flow and user experience.
1
64
Developed a full-stack language learning application tailored for Luxembourgish, combining speech recognition, natural language understanding, and generative AI. Fine-tuned OpenAI’s Whisper model for accurate Luxembourgish transcription and built a custom text-to-speech (TTS) engine for realistic audio feedback. A RAG-based architecture enables the app to answer user queries contextually, making learning highly interactive. The frontend is built with React, while Flask powers the backend. Designed to deliver an immersive, conversation-driven auditory learning experience.
1
110
Hey Contra!
Excited to finally be here and connect with builders, founders, and innovators from around the world.
I'm Osman, an AI Engineer specializing in AI Agents, LLM Applications, Automation Systems, and Full-Stack Development. Over the past 3+ years, I've helped businesses transform ideas into intelligent products using OpenAI, Gemini, LangChain, LangGraph, FastAPI, Django, and modern cloud technologies.
Some of the solutions I've built include:
• AI Agents and Multi-Agent Systems
• RAG Applications with Private Knowledge Bases
• AI-Powered SaaS Products
• Automation Workflows with n8n, Zapier, and Make
• Voice AI Agents with Twilio and ElevenLabs
• Custom Chatbots and Internal AI Tools
• Data Automation and Web Scraping Systems
I enjoy solving complex problems and building products that create real business value—not just demos.
Looking forward to connecting with founders, startups, agencies, and teams working on exciting AI projects.
If you're building something ambitious with AI, let's talk.
1
132
Worked on an RLHF (Reinforcement Learning from Human Feedback) pipeline focused on dataset creation, data annotation, and model evaluation. My role involved designing and curating high-quality prompt datasets, reviewing AI-generated responses, and providing structured feedback based on accuracy, relevance, safety, and helpfulness. Contributed to improving model performance by ensuring consistent evaluation standards and high-quality human feedback for training alignment and refinement.
1
104
Trained a DreamBooth LoRA model to generate high-quality, personalized image outputs with consistent subject identity across different prompts and styles. The project involved dataset preparation, image captioning, and fine-tuning diffusion models using LoRA for efficient training and deployment. The solution enables fast generation of customized visuals while preserving subject consistency, style control, and high fidelity, suitable for creative, branding, and content generation use cases.
1
95
Fine-tuned a GPT-based language model to generate stories aligned with individual user writing styles. The project involved collecting and structuring user-specific writing samples, training the model to learn tone, vocabulary, and narrative patterns, and optimizing it for coherent long-form storytelling. The system can adapt to different authors’ styles, producing personalized and context-aware stories while maintaining consistency, creativity, and fluency across diverse prompts.
1
94
Fine-tuned OpenAI Whisper model on domain-specific medical audio data to improve transcription accuracy for clinical and healthcare use cases. The project involved preprocessing medical speech datasets, handling noise and terminology challenges, and optimizing the model for improved recognition of medical vocabulary, accents, and context-heavy conversations. Delivered a robust speech-to-text system capable of producing highly accurate, structured transcriptions suitable for documentation, reporting, and downstream healthcare applications.
0
84
Built an intelligent inventory management system that automates stock ordering using machine learning and AI agents. Leveraging an XGBoost-based forecasting model, the system predicts future inventory demand and proactively places purchase orders when shortages are detected. The backend is powered by Django, integrated with AWS-hosted datasets for scalability and real-time data access. AI agents handle autonomous procurement decisions, reducing manual oversight and streamlining supply chain operations for greater efficiency and accuracy.
0
87
Developed a healthcare assistant application using Django (backend) and React (frontend). Users upload their medical records, and the system suggests medications based on historical data and symptoms. It also sends emergency alerts to nearby doctors via email for serious cases. PostgreSQL and OpenAI’s function calling feature were employed for data storage and automation.
0
97