Abdullah T.
Research Engineer @Quantimb Lab
Signup · Get unlimited contacts
WORK HISTORY
Research Engineer @Quantimb Lab
Toronto, ON, CA
I build performance-optimized computer vision pipelines for live-cell tracking in time-lapse microscopy, enabling quantitative analysis of cell morphology and motility relevant to cancer progression. I work with high-resolution imagery and large temporal datasets, focusing on efficient preprocessing, robust inference, and reproducible evaluation across staining protocols and imaging modalities. I package workflows in Docker for consistent runs across environments, and optimize for real-time constraints using GPU-aware parallelism and memory-efficient implementations.In addition, I develop NLP workflows for biomedical text extracting structured signals from papers, protocols, and lab notes using transformer-based models (e.g, classification, entity extraction, retrieval/RAG). I design evaluation pipelines and data curation/labeling strategies to ensure reliable performance across domains and terminology shifts.
EDUCATION
York University
Masters in applied sciences, Electrical and Computer Engineering
National University of Sciences and Technology (NUST)
Bachelors in Electrical Engineering
ABOUT ABDULLAH T.
Machine Learning Engineer with 3+ years of experience working on AI-driven applications across LLMs, generative models, and foundation-model workflows.Strong in Python and PyTorch, with experience taking models from experimentation to evaluation and deployment in real pipelines.Always open to connecting and collaborating on impactful GenAI and applied ML projectsI am excited to apply these skills to LLM and agentic AI use cases at enterprise scale, with a focus on retrieval and indexing, robust evaluation, and human-in-the-loop feedback.Keywords: Python, PyTorch, data pipelines, chunking (RAG), evaluation, Docker, Linux, GPU profiling/optimization, HPC/distributed compute, LLM & RAG familiarity, vector databases familiarity.
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.