Description

How I can help: I help teams turn messy, multi-source data into decisions — building analysis pipelines, wrangling large or unconventional datasets, and managing the timelines and deliverables around data-heavy projects. If you need someone who can both run the project and actually understand the data, that's my lane.

What makes me stand out: I did my undergrad in Chemical and Biological Engineering at Princeton, then a PhD combining machine learning with biotechnology — so I've spent years working at the intersection of hard science and applied ML, not just one or the other. I'm currently a postdoctoral researcher building deep learning models that fuse satellite and genomic data to predict ocean ecosystems, and I've also founded and run my own company, so I know what it's like to own a deliverable end to end, not just hand off a slide. I'm a hard worker with a genuine love for complex, gnarly data — the kind of project most people avoid is usually the one I find interesting. Typical work: data pipeline design, statistical/ML analysis, project and timeline management, and translating technical findings into something a non-technical stakeholder can actually use.

Languages

English
Native or bilingual

Workplace preferences

Can work on-site

Boston (up to 50km)

Lawrence Berkeley National Laboratory (LBNL)
AI/ML
January 2022 - January 2023 (1 year)
• • Conducted a large-scale metagenomics study spanning 20,712 global metagenomes; extracted and clustered nearly 18 million sensory domains with MMseqs2 to build a sensor taxonomy across ecosystems.
• • Built gradient-boosted machine learning models achieving 87% ecosystem-classification accuracy and strong predictive performance for selected environmental parameters; used feature-importance analyses to prioritize biologically informative sensors.
National Oceanic and Atmospheric Administration (NOAA)
AI/Deep Learning
January 2023 - January 2024 (1 year)
• • Evaluated DeepMicrobes and ResNet architectures for taxonomic classification of marine metagenomes using simulated reads derived from 1,267 marine genomes.
• • Built training, testing, and benchmarking pipelines using GPUs and marine reference databases, and compared deep-learning performance against standard taxonomic tools.
Syngenta
ML/AI
January 2023 - January 2024 (1 year)
• • Applied nucleotide transformer and deep-learning models to support enhancer prediction, intron-splicing analysis, and genome-editing strategy in plants.
• • Built bioinformatics workflows for RNA-seq and STARR-seq analysis using PyTorch, STAR, bedtools, rnafold, samtools, NumPy, scikit-learn, and SciPy.