Software Engineer | AI/ML Enthusiast

I build AI-powered applications and end-to-end systems that leverage LLMs, RAG, and intelligent pipelines for real-world problems. Passionate about designing scalable AI solutions and integrating data-driven insights into impactful products.

• Develop production-grade AI platforms with tool-calling LLMs for healthcare, jobs, and productivity applications.
• Build Retrieval-Augmented Generation (RAG) systems and intelligent pipelines for knowledge-driven applications.
• Integrate APIs and backend systems to create fully functional AI-assisted products.
• Collaborate on deploying scalable AI solutions with CI/CD, containerization, and cloud services.

Python, AWS ECS, DynamoDB, PostgreSQL, Lambda, Mem0

• AI-powered chatbot to manage patient data (symptoms, meals, diagnoses, treatments, allergies).
• Personalized meal recommendations with Instacart and CVS Pharmacy integration for prescription refills.
• “For You” page recommending music, podcasts, and posts based on patient context.
• Scalable AWS deployment using ECS, Lambda, CloudWatch, Batch, DMS, Secrets Manager.

RAG, LangChain, Gemini Flash, Qdrant

• RAG system for hackathon project ideas, simulating a Vitalik Buterin agent.
• Used BGE-small embeddings and Gemini Flash 1.5 Pro for context-aware generation.

Scrapy, BeautifulSoup4, Qdrant, Gemini Flash

• Scraped and structured job listings from Pakistani sites.
• Integrated LLMs to provide personalized job insights via semantic search.

Python, Flask, Scikit-Learn

• Random Forest model achieving 86% accuracy for predicting customer churn.
• Deployed as a Flask API for real-time retention insights.

Python, NLP, MongoDB, Word2Vec

• Scraped news articles, categorized using NLP, and built a personalized recommendation engine.

Associate Software Engineer | Devsinc
June 2025 – Present

• Built and deployed a production-grade AI healthcare platform leveraging ReAct orchestration with LLMs.
• Integrated CI/CD pipelines on AWS and Docker containers for consistent deployments.
• Achieved ~40% reduction in LLM costs while improving system reliability.
• Developed backend services on FastAPI and cloud infrastructure (AWS ECS, Lambda, CloudWatch, DynamoDB).
• Collaborated on AI pipelines leveraging vector databases and RAG for structured reasoning and personalized recommendations.

Artificial Intelligence Teacher Assistant | FAST NUCES Lahore
Jan 2025 – June 2025

• Assisted in teaching AI concepts, designed assignments, and supported students in ML pipelines and model evaluation.