Sommelier is a blockchain protocol for executing automated trading strategies on-chain.

❏ Leveraging: Golang, Cosmos SDK, Python, Solidity, TypeScript, Google Cloud Platform

❏ Creating and deploying live trading strategies for on-chain execution: Sommelier Protocol's Cellars.

❏ Indexing, organizing, and building APIs to serve event data emitted from smart contracts (AssemblyScript + GraphQL)

❏ Developing robust backtesting infrastructure and a scalable DeFi research pipeline

❏ Performed clustering and unsupervised topic modeling with survey responses for 2 IBM product teams

❏ Wrangled terabytes of data made up of click streams, product usage, and NPS data to derive actionable insights

❏ Regularly presented visualizations and results to stakeholders, the VP of Client Advocacy, and other leadership

❏ Leveraged: Sentence BERT, Latent Dirichlet Allocation (LDA), NLTK, Gensim, Plotly, PyTorch, SQL, IBM DB2

❏ Developed novel ML applications to automate portions of the doctor-patient interaction with NLP

❏ Advised and implemented necessary DevOps changes with Docker and Kubernetes

❏ Wrote containerized applications, RESTful web microservices, and APIs with Spring Boot and Java

❏ Leveraged: Apache Spark (PySpark), Spring Boot, Java, Docker, Kubernetes, SQL, PostgreSQL, MongoDB, PyTorch

❏ Applied neural networks with PyTorch to predict 3 phenotypes of Sprague Dawley rats based only on genetic variants (SNPs) and transcriptome wide associations

❏ Simulated rat genomes to create additional training data with generative adversarial networks (GANs), improving accuracy by 15%

❏ Utilized the High-Performance Computing cluster to leverage CUDA GPUs, interfacing with PyTorch Lightning

❏ Presented results in Columbia University’s Computer Science Research Colloquy

❏ Investigated deep learning's viability as a replacement for traditional polygenic risk metrics, benchmarking against 3 state-of-the-art classifiers - Under the supervision of Dr. Itsik Pe'er