Hi,
I am currently a Software/Data engineer with expertise in productionising machine learning models, building REST APIs, running AWS infrastructure and building data pipelines for companies in the banking, pharmaceutical and media industries. Previously, I taught data engineering concepts at University College London.
My expertise includes working with the following technology stack:
Python, FastAPI, Apache Spark, PostgreSQL, MongoDB, AWS, Apache Airflow, Docker, Jenkins, GitHub Actions, MLflow, Terraform, Kubernetes, ArgoCD, Argo Workflows and React.js.
Led engineering team in building an in-house machine learning infrastructure platform for forward deployments
• Contributed to the open-source ColabFold repository, improving database download from 1 week to 1 hour
• Led protein sequence design project by deploying AlphaFold, ColabFold 1TB RAM server and orchestrating other
protein engineering algorithms with AWS SageMaker and FSx for Lustre
• Managed Kubernetes clusters on AWS, enforced infrastructure as code, GitOps and CI/CD best practices with ArgoCD,
Helm, Terraform and CircleCI
• Designed, developed and deployed fine-grained access control across the product using Keycloak, Kubernetes and AWS
• Delivered a talk about AI applications and challenges for the London Business School MBA class
• Developed and deployed a full stack web application leveraging GPUs for neural network image classification using Flask,
AWS, MongoDB, MLflow, ArgoCD, Docker and Kubernetes
• Built oncology data pipeline for patient overall survival prediction using Apache Spark, Metaflow and OmegaConf
• Led engineering team towards building an SDK, API and full-stack application for mRNA sequence optimization
• Designed and created Docker and Kubernetes training programme content for intermediate level practitioners across the firm