Work Experience

Syska Hennessy Group

Software Engineer

April 2023 – March 2024, September 2024 – Present

New York, USA

Built POC chatbot: FastAPI backend with Docker, hosted on GCP; auto-scaling with Cloud Run containers.
Led production chatbot deployment on Kubernetes, scaling to 200+ concurrent users.
Hosted vector database on K8s through Azure with cron job to automatically fetch and upload new articles into knowledge base.
Architecting legal form automation system, reducing workflow time by 20%. Lead team on this project.
Created React frontend and Flask backend for web app that used XGBoost to forecast cooling expenses for data centers.

AI Researcher in Residence

April 2024 – September 2024

San Francisco, USA

Researched effects of different chunking methods in Retrieval Augmented Generation (RAG).
Developed a method to generate synthetic evaluation sets letting you test which chunker has best retrieval scores for a given type of corpora.
Improved recall up to ~10% with optimized chunking strategies.
Produced technical paper which was praised by Christopher Manning, director of Stanford AI Labs.
GitHub repository gained over 280 stars and has had multiple community contributions.

CTO

August 2023 - January 2024

San Francisco, USA

Co-Founded Project Chiron Inc, an AI tutor company to teach all kids maths, and raised $47,000.
Implemented DevOps: rapid development cycle with Cloud Build, GitHub triggers for automatic builds.
Managed SQL server; optimized for 150,000+ rows of user data for efficient usage statistics algorithms.
Implemented Redis cache for faster data delivery.
Built Svelte frontend; integrated OpenAI API. Achieved 100 active users with average weekly usage of 80 hours.
Implemented Stripe payment system.

Software Engineer

May 2020 - October 2021

San Francisco, USA

Programmed inventory management software on Unity3D using C# that connects with Amazon Web Service (AWS) SQL databases.
Exported Excel financial documents that was used in projects with Facebook.

Software Engineer

July 2019 - May 2020

San Francisco, USA

Created TensorFlow Deep Reinforcement Learning (DRL) agent for optimized pipe placement, enhancing hallway space.
Project achieved 1,000+ LinkedIn likes and attracted new clients.
Conceptualized and coded a program in Python using OpenCV for counting symbols in architectural blueprints.
Further optimized it in C# for commercial release.