I specialize in architecting large-scale ML systems and building distributed computing solutions. With experience at Northern Trust, Oracle, and John Deere, I've developed expertise in automated code migration, ML pipelines, and event-driven microservices. Whether it's reducing manual conversion time by 85% across 500K+ lines of legacy code or handling 100M+ daily trading data points, I'm passionate about leveraging cutting-edge technologies to drive efficiency and innovation.
Northern Trust
May 2023 - Present
Chicago, IL
Oracle
May 2022 - August 2022
Seattle, WA
John Deere
August 2021 - November 2021
Waterloo, IA
PricewaterhouseCoopers
June 2021 - July 2021
New York, NY
Gramaner
November 2020 - March 2021
Princeton, NJ
Instahub
May 2020 - August 2020
Philadelphia, PA
Technical Expertise
Python
Implemented and tested KNN, Naïve Bayes, and LR on dataset of 60,000 training images and 10,000 test images for digit classification reporting error of less than 2%. Optimized PReLU MLP with 4 layers and 256 nodes per layer on MRI image reconstruction with ∝ being learned from training data using backpropagation to minimize loss function.
Python / HuggingFace / GPT2
Leveraged LLM using Huggingface utilizing techniques including attention mechanisms, self-attention, and transformer architecture to build an AI text generator. AI text generator can infer semantics and contextualize information based on input prompts.
ASML / C++
Built Linux like operating system incorporating GDT, IDT, basic paging support for tasks, separate 4 MB pages for the kernel and applications. Included device initialization, system call interface along with ten system calls.
Python (Pandas, SciPy, Seaborn)
Implemented Monte Carlo simulation to estimate the value of a European call option using Python. The simulation involved generating random stock price paths, calculating option payoffs, and averaging these payoffs to estimate the option's value.