Using AWS, LLMs (Large Language Models), Django (backend), and Next.js/React (frontend) to build applications for automating and scaling the candidate-screening process. Designing dashboards, repository analysis tools, and database connection APIs to efficiently handle and visualize relevant data.

• Using LLMs to dynamically generate assessments from job descriptions – delivering real-time questions, and adapting difficulty based on responses, short-listing high-quality candidates with minimal effort
• Developing a tool to analyze users’ GitHub repositories and surface non-technical insights on coding proficiency, test coverage, open-source collaboration, and adherence to modern standards
• Creating a dashboard that transforms candidate-resume knowledge graphs into interactive clusters with drill-down capabilities, allowing recruiters to pinpoint skill gaps and trends in their database

Used Python, FastAPI, Web3.py, and an AWS pipeline to develop software focused on blockchain transaction analysis, analytics on consumer habits, and creating comprehensive visual dashboards. Introduced Snowflake to analyze large datasets before ML ingestion, enabling scalable, real-time data insights.

• Designed and built the initial infrastructure using Django, AWS SageMaker, S3, SQS, and Lambdas to facilitate the asynchronous analysis of millions of blockchain transactions and visualizations of key metrics
• Containerized a Telegram bot using AWS infrastructure to manage its deployment, resulting in a multi–purpose Generative AI bot that serviced members with zero downtime
• Used a K-means clustering algorithm on AWS SageMaker to identify patterns in client transactions, followed by an LLM via AWS Bedrock for labeling and summarization – yielding new insights that shaped development strategies

Used Python, Web3.py, FastAPI, Docker, ML models, built integrations tests, and more to improve company productivity, debug and test code, and drive sales. Researched and presented potential investments to stakeholders, and worked with clients as a pre-launch advisor.

• Helped improve team efficiency by over 40% by spotting slow points in our workflow and building custom bots with Python, FastAPI, and Docker to automatically deliver investment-related information to customers
• Developed token-tracking software using K-means clustering and a XGBoost ML models to monitor presale investor activity, gaining insights into investor patterns – resulting in a product to advise clients, increasing AUM by 15%
• Lead the development of an incubated project, earning major awards and securing partnerships to enable carbon offset solutions for digital assets and financial services

Played a pivotal role in strategizing for sales growth, identifying process inefficiencies, and developing Python-based frameworks (Django, RESTful APIs, ML models) and AWS to improve business efficiency, earning a 5% ownership stake in the company as recognition of my contributions over the years.

• Used an XGBoost ML model to adjust prices on website, eBay, and Amazon using historical sales data, competitor pricing, and market trends – creating real-time pricing strategies that maximized profit and volume
• Built software using AWS infrastructure that hooked into online platforms like Amazon, Ebay etc., and dynamically listed products based on signals of which site yielded higher returns – resulting in a 25% increase for online sale
• Used Django, Python, and JavaScript (React) to create a responsive website that made sales processes smoother and helped analyze customer behavior – leading to a ~20% bump in both efficiency and sales