Peter St John
Machine Learning Engineer (Digital Biology) at NVIDIA
Golden, Colorado, United States
Summary
👤
Senior🎓
Top SchoolPeter St John is a machine learning engineer with 12 years of experience applying ML to digital biology, metabolic modeling, and computational chemistry, currently accelerating workflows on NVIDIA’s BioNeMo team after contributing to autonomous vehicle perception ML. He led multi-institutional, multi-million-dollar research programs at NREL, delivered high-impact papers in Nature journals, and architected production ML services—pretraining a BERT-style model on 261M protein sequences and deploying containerized web apps with CI/CD for thousands of users. His open-source contributions include core improvements to COBRApy for constraint-based metabolic modeling and enhancements to cclib’s Gaussian parser, reflecting deep domain knowledge in biochemical data pipelines. Combining a PhD in Chemical Engineering with hands-on software engineering, he bridges wet-lab insight and scalable ML systems to turn complex biological questions into deployable solutions.
12 years of coding experience
7 years of employment as a software developer
Bachelor's Degree, Chemical and Biological Engineering, GPA: 3.79, Bachelor's Degree, Chemical and Biological Engineering, GPA: 3.79 at Tufts UniversityHigh School, High School at Choate Rosemary HallDoctor of Philosophy (Ph.D.), Chemical Engineering, Doctor of Philosophy (Ph.D.), Chemical Engineering at University of California, Santa Barbara
Stackoverflow
531reputation
34kreached
7answers
5questions
Github Skills (21)
quantum-chemistry10
parser10
python10
testing10
constraint-satisfaction10
computational-chemistry10
constraint-layout10
constraint10
parsing10
parse10
modeling10
bioinformatics9
sbml8
inkscape6
graphviz6
Programming languages (16)
Github contributions (5)
opencobra/cobrapy
Feb 2016 - Oct 2018
COBRApy is a package for constraint-based modeling of metabolic networks.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:42 commits, 44 PRs, 11 pushes in 2 years 8 months
Contributions summary:Peter primarily contributed to the core functionality of the COBRApy package, focusing on implementing features related to the modeling of metabolic networks. Their work involved adding new functionalities such as setters for elements within the Metabolite class and adding summary methods to the Model and Metabolite classes to provide more insight into the FBA solutions. The user also made improvements to the parsimonious FBA implementation and fixed issues related to the model summary methods, demonstrating a strong understanding of the core concepts in constraint-based modeling.
pythonsystems-biologysimulationsbml-simulationbioinformatics
cclib/cclib
Nov 2019 - Mar 2020
Parsers and algorithms for computational chemistry logfiles
Role in this project:Back-end Developer & QA Engineer
Back-end Developer & QA EngineerContributions:6 commits, 1 PR, 5 comments in 4 months
Contributions summary:Peter primarily contributed to the `cclib` project by enhancing the Gaussian parser. They focused on parsing and incorporating atomic spin information from Gaussian log files, addressing issues in existing parsing logic. Their work involved adding new parsing functionalities, modifying existing code to handle different log file formats, and implementing tests to ensure the accuracy of the spin-related data extraction. Furthermore, they improved the parsing of charge information.
logfilescheminformaticspythonchemistryparsers
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.