Sound familiar?
Too many formulation rounds
Each iteration takes weeks. You're running experiments that AI could have helped de-prioritize on day one.
Literature overload
Cross-disciplinary research means hundreds of papers. Your team spends days reading instead of discovering.
AI tools that don't stick
Everyone tried ChatGPT. Nobody built a real workflow. The gains stayed on someone's laptop.
Services
Each engagement is scoped around your team's specific workflows and goals.
Custom Tool Build
You bring a specific bottleneck in your formulation or process workflow. I build a working tool (web app, notebook, or internal dashboard) you and your team can actually use.
- ✓Scoping call (60 min) to define the problem
- ✓4–6 week build cycle with milestone check-ins
- ✓Working deliverable + documentation
- ✓30-day post-launch support
Workflow Integration Sprint
Your team already uses AI ad hoc. I embed AI workflows into your actual research loop — literature mining, DOE setup, data analysis — so the gains stick after I leave.
- ✓2–3 week engagement
- ✓Custom workflows tied to your tools
- ✓Team walkthrough + operations manual
- ✓Post-engagement Q&A
Fractional Research Engineer
Ongoing build + advisory for teams that need an embedded AI-chemistry hybrid without hiring a full-time role.
- ✓20–40 hours/month
- ✓Mix of building, iteration, and technical guidance
- ✓Direct Slack/email access
- ✓Monthly scope review
Currently building out early case studies. Early engagement slots available — see Services below.
About
I'm a chemistry PhD and materials scientist who spent 15 years working at the intersection of hydrogels, polymer chemistry, RNA biology, and microfluidics — and the last few years figuring out how AI actually changes the way we do research. Not in theory. In practice, inside real labs.
My edge isn't that I know AI. It's that I know biomaterials research deeply enough to know which problems are worth solving — and which AI tools are actually useful versus just impressive in a demo.
Projects
Tools I built at the intersection of materials science and AI.
Polymer Tg Predictor
A machine learning model that predicts glass transition temperature (Tg) of polymer adhesives from monomer composition — helping formulation chemists narrow candidates before synthesis.
Helps formulation teams eliminate low-probability candidates before synthesis — reducing early-stage screening rounds by up to 60%.
IVT Optimizer
An AI-assisted tool for optimizing in vitro transcription (IVT) yields. Automates DOE analysis and provides data-driven recommendations for mRNA production parameters.
Cuts IVT parameter optimization from days to hours — automating DOE analysis that typically requires multiple manual experiment cycles.
Currently Exploring
- ◆Aqueous polymer inverse design for tissue adhesion and wound care
- ◆AI-assisted LNP formulation and mRNA process optimization
- ◆Continuous-flow process design for specialty biologics
If any of these sound like your problem, I'd love to hear about it. Even if you're not buying.
Writing
Occasionally, I write about what I'm learning at the intersection of AI and biomaterials research.
Why most AI tools don't stick in research workflows
A look at what separates demos from tools that teams actually use.
DOE + AI: replacing intuition with data in formulation R&D
How combining design of experiments with machine learning changes the iteration loop.
mRNA process development in the age of LLMs
What language models can and can't do for bioprocess engineers today.
Common Questions
Let's Talk
Not sure if this applies to your team? No pitch — just a real conversation about your workflows.
Send an Email