Background
My career spans three intersecting domains. I spent 7+ years as a PhD and postdoctoral researcher in physics and astrophysics, applying ML and advanced statistical methods to petabyte-scale datasets and publishing findings in top peer-reviewed journals. After academia, I spent 3+ years creating AWS AI/ML developer documentation, API references, and information architecture for Amazon SageMaker services. While at AWS, I designed and built AI-powered tools using LLMs, MCP Protocol, and Python to streamline complex workflows.
What Sets My Work Apart
I combine deep technical understanding with clear, structured communication. Whether building AI-powered automation pipelines, documenting ML workflows for developers, or translating astrophysics research results for international research audiences, I focus on understanding the problem space and delivering evidence-based solutions.
Technical Communication
At Amazon Web Services, I owned and created documentation for major SageMaker AI features, working directly with engineering teams to validate technical accuracy. My work spanned product documentation, architecture guides, and cross-functional process improvements that impacted documentation AWS-wide.
AI-Powered Tools
At AWS, I designed and built AI-powered tools that automated complex workflows, from multi-stage drafting pipelines to agentic ticket resolution systems. I also created and taught AI training courses, achieving 80%+ adoption rates and 30%+ productivity gains among participants.
Research & Data Science
My doctoral and postdoctoral research focused on applying ML and statistical methods to massive cosmological datasets, including dark matter halo dynamics and weak gravitational lensing. This resulted in the discovery and first measurement of a novel physically meaningful dark matter halo parameter. I published 4 first-author papers in the Monthly Notices of the Royal Astronomical Society (MNRAS), applying end-to-end data science methods to petabyte-scale datasets.
Core Skills
- AI-powered tools: Building LLM-powered tools, prompt engineering, agentic systems, MCP Protocol integration
- Technical communication: Developer documentation, API references, information architecture, docs-as-code workflows
- Data science: Statistical modeling, MCMC sampling, Bayesian inference, ML pipelines, Python
- Data visualization: Publication-quality figures communicating multi-dimensional statistical concepts
- Cross-functional collaboration: Working across engineering, product, and research teams to deliver technical work
- Technical depth: Hands-on with codebases, APIs, simulations, and systems to ensure accuracy and quality