Share Profile
Fatima Dossa
Aspiration Statement
I am interested in applying AI and Machine Learning to solve real-world problems through data-driven analysis. I aim to build intelligent, scalable systems grounded in strong technical and analytical thinking.
Core Skills
- Data Analysis & Visualization (Pandas, NumPy, Looker Studio)
- Machine Learning
- Python
- SQL (BigQuery)
- Statistical Analysis
Core Competencies
- Acts with Ownership
- Agility
- Planning
- Takes Initiative
Preferred Career Paths
First priority: AI / Machine Learning Engineer
Second priority: Data Scientist / Applied AI Analyst
Third priority: AI Research / Applied Research Associate
Experience
Leadership / Meta-curricular
- President, Wise (Women in Science and Engineering)
- Research and Marketing Lead, Huaic (Habib University Artificial Intelligence Chapter)
- Treasurer, Sports & Recreational Club
- Habib University Table Tennis Competition Lead, Sports & Recreational Club
- Pr Cabinet Team Member, Habib University Student Government
Internship / Volunteer Work
- Technical Trainer, Codeschool (January 2026)
- Lead Instructor, Codeschool (March 2025 – April 2026)
- Research Fellow, Girlswhoml (August – November 2025)
- Business Intelligence Intern, Waada (June – July 2024)
Final Year Project
Project Title
Al Khidmat Public Chat Portal
Description
The AI-powered multilingual chat portal for Alkhidmat Foundation addresses manual query-handling delays by providing a centralized, inclusive solution. Using a Self-RAG (Retrieval-Augmented Generation) and Agentic AI pipeline, it automates responses for donor, healthcare, and general domains in English, Urdu, and Roman Urdu. The system utilizes multilingual-e5-base embeddings and pgvector for semantic search, with OpenAI and Alif for generation. To ensure accuracy, it employs a domain classification and confidence scoring engine that fuses retrieval quality with token probability. Key benefits include 24/7 accessibility for underserved communities, reduced staff workload, and automatic human-agent escalation for complex queries. Moreover, there is a dedicated admin dashboard to view LLM analytics and update the RAG Knowledge Base.
Project Pictures
