I’m a data scientist and AI engineer with 10+ years of experience building scientific computing, data, and AI systems at the National Institutes of Health. I work on LLMs, retrieval augmented generation (RAG), cloud infrastructure, and scientific computing, mostly in environmental health and toxicology. My background in toxicogenomics and HPC means I can talk to the scientists and still ship the production system. I’m an enrolled member of the Chippewa Cree Tribe of the Rocky Boy Reservation in Montana, a descendant of the Salish, Kootenai, and Pend d’Oreille Tribes of the Flathead Reservation, a tribal college graduate, and an advocate for Indigenous data sovereignty. I also offer consulting, especially on Indigenous data sovereignty.
I’m currently looking for work. I’m interested in roles involving LLMs, RAG, data science, or cloud AI infrastructure, especially in science or academia. If you think I’d be a good fit, please email me.
Most recently
Until September 2026, I was a Computer and Information Research Scientist – SME at Dynanet Corporation. I led AI/LLM development and AWS cloud infrastructure strategy for the CAMERA project at the National Institute of Environmental Health Sciences (NIEHS). That covered LLM-powered search with knowledge base integration, AI-driven automation for curating filters and facets, PubMed literature workflows, and moving the project to a secure, NIH-compliant AWS environment.
How I got here
I spent about ten years at NIEHS before joining Dynanet:
- Division of Translational Toxicology (2022–2025). I received a $150,000 NIH NOSI grant to explore LLMs and AI in the cloud. I deployed an internal, open source LLM interface and API, built RAG pipelines on vector databases (Chroma, FAISS, pgvector), and wrote the NIEHS Scientific Developer’s Guide for onboarding scientific developers.
- Office of Data Science (2018–2022). I ran Posit Team for the institute’s notebooks, Shiny apps, and APIs. I also managed the NIEHS GitHub organization, automated reproducible pipelines with
targets, Quarto, renv, and Docker, and taught Cytoscape workshops on biological network analysis. - National Toxicology Program (2015–2018). As a postbaccalaureate IRTA fellow, I helped develop and document BMDExpress 2.0 and did toxicogenomic analysis with DrugMatrix, ToxFX, and Cytoscape.
Before that, I earned a B.S. with a focus in Environmental Health from Salish Kootenai College in Pablo, Montana. While there I tutored in the SEM Lab, worked in the environmental chemistry lab measuring mercury, arsenic, and selenium, and interned with the EPA (Regions 9 and 10) and NIEHS.
Things I like working with
- AI / LLMs: LangChain, LangGraph, LlamaIndex, LangFuse, promptfoo
- Data: Python, R, SQL, vector and graph databases, knowledge graphs
- Infrastructure: AWS, Docker, CI/CD, HPC (Slurm, Apptainer)
- Publishing: Quarto, which I’ll recommend to anyone who asks
My full work history and publications are on my resume.