Dedicated Machine Learning Engineer with 3 years of experience in the cybersecurity industry and a versatile skill set spanning ML model development, AI agents, prompt engineering, and web development. Proficient in deploying and optimizing ML models for large-scale datasets, with demonstrable knowledge in Python. Experienced at designing efficient systems and problem-solving complex challenges, committed to clean engineering practices and agile methodologies. Currently advancing skills with AWS and cybersecurity certifications to deepen technical expertise.
The last 3 years have been spent working as part of a small team on an anti-piracy system, called Evergreen, for a global book and scientific journal publishing organisation. This system collates 3rd party data from not only the publisher itself but from supporting organisations such as doi.org and Crossref.org (via API calls) to enrich the data supplied by the publisher. Log files from the publisher's firewall are ingested into Evergreen from their S3 storage locations and analysed for anomalous behaviours. Alert thresholds are also built into Evergreen to create firewall rules in the event of one or more defined behaviours being detected
Fraudulent Download Detection System, Built an end-to-end ML pipeline using Python and scikit-learn, processing billions of records to detect anomalies with high precision. LLM Deployment for AI Agents, Implemented and optimized LLaMA3 models in Python, leveraging GPU resources for high-performance applications. Designed AI agents for automation in various operational workflows, ensuring seamless functionality. MLOps Integration, Automated model retraining and monitoring pipelines to ensure performance consistency. Web Application Development, Built full-stack web applications integrating ML models into user-friendly dashboards. Used React.js and Flask for efficient interface and API development.