The project has grown considerably. I am proud to now lead as a Full Stack Tech Lead and Project Manager. Driving the selection and onboarding of new recruits has now become a core responsibility for me, as well as overseeing the operations and managing the expanding team of front and back-end developers. We consistently employ Agile practices during our processes, and I also effectively fill the role of Scrum Master within our team.

Due to the advancements in AI, stakeholders have decided to research and implement machine learning (ML) solutions to improve the daily activities of an editorial team. This is aimed at creating a more productive workflow.My task involved studying and researching Natural Language Processing (NLP) techniques in the context of financial crime, that would ultimately benefit the project contributors and clients.During this process my responsibilities included:- Cleaning and analysing the entire corpus of articles.- Feature engineering based on existing categories, tags and keywords.- Training and evaluating machine learning models for text classification, summarisation and entity extraction using the new features.- Clustering and topic generation for identifying new themes.- Building a recommendation system using vector embeddings and cosine similarity.- Working closely with and guiding editors while collecting training data.- Prompt engineering utilizing zero shot, few shot and chain of thought (CoT) techniques with large language models (LLM).- Setting up a Python web server for hosting proprietary models and implementations.- Planning and creating API routes for communication between back-end systems.Technologies and tools used:- OpenAI GPT 3 / 3.5 / 4 and function calling API- Hugging Face- Python- Flask- Pinecone- LlamaIndex- Transformers- SpaCy- Sklearn

With the below features rolled out in production we have continued exploring other exciting areas of Ai that could offer value to the company and clients.The areas I was exploring include:- Retrieval augmented generation (RAG).- Agents and tools in the context of a chat interface for interacting with the portal and for an efficient way of consuming the content that's increasingly denser - Financial risk alerting tool using close to real time data with a stack of machine learning models serving as filters alongside LLMs.- Cost reduction using the best performing open-source large language models with fewer parameters (3-7b), but large context window (>8k) where "training" using few-shot prompting gave close to production results.

My task after being hired was the creation of a website (SPA) for showcasing a human curated set of articles related to financial crime. During this process my responsibilities included (not limited to):On the client front-end:- Designing the user interface according to specifications- Planning and researching the most optimal frameworks and libraries for building the UI- Laying down coding standards and configuring linters- Building the application using best practices- Setting up build pipelines- Mobile and speed optimisations- Building a recommendation system based on bookmarks of a user with the use of vector embeddings and cosine similarity- Implementing a full text search feature with boolean operators.On the admin front-end (similar to the above and the following):- Building a secure portal for administrators for managing the content- Building an interface for viewing, editing and sharing internally content captured by our web crawler This component also includes controls for data labeling by editors, which is used to collect data for further fine-tuning of the filters used by the crawler- Implementing new features according to the specifications- Building newsletter management systemBy taking a modern and minimalist approach we used the following tools and technologies:- Native web components wrapped (LitElement)- JavaScript- TypeScript- Redux- Mocha & Chai- Git- Azure blob storage- Azure Pipelines (CI/CD)- SentryOn the server side (back-end):- Planning the application stack and database schema- Planning and creating the API routes- Creating and configuring the database instance- Handling authentication- Setting up build pipelines- Laying down code standards and configuring linters- Optimising database queriesTools and technologies used:- Node.js- Express.js- Objection ORM- TypeScript- Websockets- Mocha & Chai- Sentry- Azure App Service- Azure PostgreSQL database instance- Azure Pipelines (CI/CD)- JWT

I founded WebXpert, a software engineering company that gradually began to offer a wide range of services. These services vary from creating business plans and sales strategies to software development, as well as providing storage and email hosting solutions. Over the years, we have carried out countless assignments and delivered numerous web, native, and mobile applications.The main services we offer:- Custom Software Development for tailored software solutions to meet unique business needs.- Business Planning to chart clear paths for start-up ventures.- Sales Strategy Consulting for crafting sales approaches to secure optimal outcomes.- Application Development of efficient web and mobile platforms.- Email Hosting setup for smooth and reliable communication.- Secure Storage Solutions for effective data handling.- Insightful Product Development turning bright ideas into tangible, sellable products.- IT Consultation sharing insights for boosted tech potential.- Digital Transformation guidance for an easier journey in the digital world.- Support and guidance on Cloud Services and all related queries and tasks.- Copywriting Services weaving persuasive content for varied audiences.- UI/UX Design creating intuitive user interfaces for superior digital experiences.Programming skills:- Languages:- JavaScript- Python- JavaSoftware as a service (SaaS, PaaS):- Azure SQL Database- Azure DevOps- Azure Functions- Azure App Service- AWS Elastic Beanstalk- AWS Lambda- AWS EC2Databases:- MySQL- PostgreSQL- GraphQl- MongoDBBack-end frameworks:- Node.js- Apache- Express.js- PHP- PostfixSDK & EDI:- Android Studio- Atom- VSCodeFrontend frameworks:- LitElement- Vue- Blade- LESS- CSSVersion Control Systems:- GitOther skills:- Linux- Bash

Hired by the agency for the creation of their portfolio website. The project heavily relied on multimedia content such as photographs and video content which was challenging at that time and required Adobe Flash for building most parts of the website. During the time spent at this company I had to maintain and enhance the project and also update the page’s content through FTP.Responsibilities:- Planning and designing the UI as well as the underlying technology stack.- Creating the front-end according to specifications, setting up the hosting environment and deploying the project.- Content management. Regularly uploading photos and videos supplied by the team of photographers at the company.- Search engine optimisations and handling cross browser compatibility.Skills:- HTML- CSS- Adobe Dreamweaver- Adobe Flash- jQuery- JavaScript- PHP- FTP