Breaking Games Externship via Extern
Completed a Pfizer externship in AI-powered document insights while growing hands-on skills to make my resume more competitive.
My portfolio features work from the Pfizer Advanced externship and related projects, demonstrating hands-on experience with document insights, data extraction, and applied AI techniques.
Built a Retrieval-Augmented Generation (RAG) AI agent to retrieve relevant data from curated life science libraries and databases. Integrated data cleaning, embedding generation, and retrieval pipelines using Pinecone and AWS. Designed the agent to provide reliable and explainable responses for life
.jpg)
Pfizer · Oct 2026 · ✅ Verified by Extern
Prototype AI-powered document intelligence with Pfizer—using OCR, LLMs, and RAG to automate real enterprise PDF workflows and build a standout portfolio project.
Completed a Pfizer externship in AI-powered document insights while growing hands-on skills to make my resume more competitive.
I am Zakia Djerrah Arib. I hold a masters degree and have some professional experience while I build my career. I am completing the Pfizer Advanced: AI-Powered Document Insights & Data Extraction externship to strengthen my resume and improve my competitiveness for jobs and internships.
Externships
SQL & Database Architecture Externship with Breaking Games
In progress
Experience
Lab operations lead
Johnson & Johnson · Oct 2022 - Dec 2023
Education
Biology engineer evaluated to Master's in biology
Biology engineering · Class of 2005
Skills
Built a Retrieval-Augmented Generation (RAG) AI agent to retrieve relevant data from curated life science libraries and databases. Integrated data cleaning, embedding generation, and retrieval pipelines using Pinecone and AWS. Designed the agent to provide reliable and explainable responses for life
✅ Verified by Extern
Prototype AI-powered document intelligence with Pfizer—using OCR, LLMs, and RAG to automate real enterprise PDF workflows and build a standout portfolio project.
The externship prototyped an AI document-insights workflow combining OCR, LLMs, and retrieval-augmented generation to process enterprise PDF documents. The work examined model behaviors and pipeline components, and produced explanatory materials about how large language models operate.
I summarized how transformer-based LLMs predict next tokens using self-attention and how fine-tuning plus reinforcement learning from human feedback improve coherence and context-awareness.
✅ Verified by Extern · ⏱️ In progress
Turn six messy CSVs into an analytics database and a Q4 dashboard that drives real business decisions. SQL + Claude.
The project consolidated six messy CSV files into a structured analytics database and produced a Q4 dashboard. The work mapped each source, normalized tables, and designed joins and keys to enable consistent reporting. Deliverables included the cleaned database schema and a dashboard fed from the transformed data.
I turned six raw CSV sources into a cleaned analytics database and used that database to build a Q4 dashboard; below are the specific tasks I completed during the externship.
